Semantic_Segmentation
-
Referring Change Detection in Remote Sensing Imagery
2025-12-12 16:57:12Yilmaz Korkmaz, Jay N. Paranjape, Celso M. de Melo, Vishal M. PatelAbstract
Change detection in remote sensing imagery is essential for applications such as urban planning, environmental monitoring, and disaster management. Traditional change detection methods typically identify all changes between two temporal images without distinguishing the types of transitions, which can lead to results that may not align with specific user needs. Although semantic change detection methods have attempted to address this by categorizing changes into predefined classes, these methods rely on rigid class definitions and fixed model architectures, making it difficult to mix datasets with different label sets or reuse models across tasks, as the output channels are tightly coupled with the number and type of semantic classes. To overcome these limitations, we introduce Referring Change Detection (RCD), which leverages natural language prompts to detect specific classes of changes in remote sensing images. By integrating language understanding with visual analysis, our approach allows users to specify the exact type of change they are interested in. However, training models for RCD is challenging due to the limited availability of annotated data and severe class imbalance in existing datasets. To address this, we propose a two-stage framework consisting of (I) \textbf{RCDNet}, a cross-modal fusion network designed for referring change detection, and (II) \textbf{RCDGen}, a diffusion-based synthetic data generation pipeline that produces realistic post-change images and change maps for a specified category using only pre-change image, without relying on semantic segmentation masks and thereby significantly lowering the barrier to scalable data creation. Experiments across multiple datasets show that our framework enables scalable and targeted change detection. Project website is here: this https URL.
Abstract (translated)
在遥感图像中进行变化检测对于城市规划、环境监测和灾害管理等应用至关重要。传统的变化检测方法通常会在两个时间点的影像之间识别所有变化，而不区分这些变化的具体类型，这可能导致的结果可能无法满足特定用户的需求。虽然语义变化检测方法试图通过将变化归类到预定义的类别来解决这一问题，但这些方法依赖于固定的类别定义和固定模型架构，使得难以混合具有不同标签集的数据集或在任务间重复使用模型，因为输出通道紧密耦合了类别数量及类型。 为克服这些问题，我们引入了基于自然语言提示的变化参考检测（RCD），它能够针对遥感图像中特定类别的变化进行识别。通过将语言理解和视觉分析相结合，我们的方法允许用户具体指定他们感兴趣的变化类型。然而，由于标注数据的有限可用性以及现有数据集中类别不平衡的问题，训练用于RCD的模型具有挑战性。 为解决这些问题，我们提出了一种两阶段框架：(I) **RCDNet**，这是一种专门针对变化参考检测设计的跨模态融合网络；(II) **RCDGen**，这是一个基于扩散的合成数据生成流水线，能够仅使用前一时间点的图像来生成特定类别的真实感变化后的影像和变化图，无需依赖语义分割掩码，并且显著降低了可扩展性创建数据的门槛。 在多个数据集上的实验表明，我们的框架能够实现规模化的、有针对性的变化检测。项目的官方网站链接：[这里](this https URL)。
URL
https://arxiv.org/abs/2512.11719
PDF
-
DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation
2025-12-12 11:07:40Mohamed Abdelsamad, Michael Ulrich, Bin Yang, Miao Zhang, Yakov Miron, Abhinav ValadaAbstract
Recent advances in self-supervised learning (SSL) have shown tremendous potential for learning 3D point cloud representations without human annotations. However, SSL for 3D point clouds still faces critical challenges due to irregular geometry, shortcut-prone reconstruction, and unbalanced semantics distribution. In this work, we propose DOS (Distilling Observable Softmaps), a novel SSL framework that self-distills semantic relevance softmaps only at observable (unmasked) points. This strategy prevents information leakage from masked regions and provides richer supervision than discrete token-to-prototype assignments. To address the challenge of unbalanced semantics in an unsupervised setting, we introduce Zipfian prototypes and incorporate them using a modified Sinkhorn-Knopp algorithm, Zipf-Sinkhorn, which enforces a power-law prior over prototype usage and modulates the sharpness of the target softmap during training. DOS outperforms current state-of-the-art methods on semantic segmentation and 3D object detection across multiple benchmarks, including nuScenes, Waymo, SemanticKITTI, ScanNet, and ScanNet200, without relying on extra data or annotations. Our results demonstrate that observable-point softmaps distillation offers a scalable and effective paradigm for learning robust 3D representations.
Abstract (translated)
最近的自监督学习（SSL）进展展示了在没有人类注释的情况下学习三维点云表示的巨大潜力。然而，由于不规则几何形状、容易出现捷径问题的重建和不平衡的语义分布，对于三维点云的SSL仍然面临严峻挑战。为此，我们提出了DOS（Distilling Observable Softmaps），这是一种新颖的SSL框架，仅在可观察（未遮罩）点上自我提炼语义相关性软映射。这种策略可以防止信息从被掩码区域泄漏，并且相比离散标记到原型分配提供了更丰富的监督信号。为了应对无监督设置中不平衡语义的问题，我们引入了齐夫定律原型并通过修改后的Sinkhorn-Knopp算法（Zipf-Sinkhorn）将其整合，该算法在原型使用上施加幂律先验并在训练过程中调节目标软映射的锐度。 DOS在nuScenes、Waymo、SemanticKITTI、ScanNet和ScanNet200等多个基准测试中，在语义分割和三维物体检测任务上超越了当前最先进的方法，且无需依赖额外的数据或注释。我们的结果表明，可观察点软映射提炼提供了一种可扩展且有效的学习稳健三维表示的范式。
URL
https://arxiv.org/abs/2512.11465
PDF
-
Out-of-Distribution Segmentation via Wasserstein-Based Evidential Uncertainty
2025-12-12 08:36:59Arnold Brosch, Abdelrahman Eldesokey, Michael Felsberg, Kira MaagAbstract
Deep neural networks achieve superior performance in semantic segmentation, but are limited to a predefined set of classes, which leads to failures when they encounter unknown objects in open-world scenarios. Recognizing and segmenting these out-of-distribution (OOD) objects is crucial for safety-critical applications such as automated driving. In this work, we present an evidence segmentation framework using a Wasserstein loss, which captures distributional distances while respecting the probability simplex geometry. Combined with Kullback-Leibler regularization and Dice structural consistency terms, our approach leads to improved OOD segmentation performance compared to uncertainty-based approaches.
Abstract (translated)
深度神经网络在语义分割方面表现出色，但它们仅限于预定义的一组类别，这导致在遇到开放世界场景中的未知对象时会出现失败。识别和分割这些分布外（OOD）的对象对于自动驾驶等安全关键应用至关重要。在这项工作中，我们提出了一种基于 Wasserstein 损失的证据分割框架，该框架能够捕捉分布距离并尊重概率单纯形几何结构。结合 Kullback-Leibler 正则化和 Dice 结构一致性术语，我们的方法在 OOD 分割性能方面优于不确定性基线方法。
URL
https://arxiv.org/abs/2512.11373
PDF
-
VFMF: World Modeling by Forecasting Vision Foundation Model Features
2025-12-12 02:10:05Gabrijel Boduljak, Yushi Lan, Christian Rupprecht, Andrea VedaldiAbstract
Forecasting from partial observations is central to world modeling. Many recent methods represent the world through images, and reduce forecasting to stochastic video generation. Although such methods excel at realism and visual fidelity, predicting pixels is computationally intensive and not directly useful in many applications, as it requires translating RGB into signals useful for decision making. An alternative approach uses features from vision foundation models (VFMs) as world representations, performing deterministic regression to predict future world states. These features can be directly translated into actionable signals such as semantic segmentation and depth, while remaining computationally efficient. However, deterministic regression averages over multiple plausible futures, undermining forecast accuracy by failing to capture uncertainty. To address this crucial limitation, we introduce a generative forecaster that performs autoregressive flow matching in VFM feature space. Our key insight is that generative modeling in this space requires encoding VFM features into a compact latent space suitable for diffusion. We show that this latent space preserves information more effectively than previously used PCA-based alternatives, both for forecasting and other applications, such as image generation. Our latent predictions can be easily decoded into multiple useful and interpretable output modalities: semantic segmentation, depth, surface normals, and even RGB. With matched architecture and compute, our method produces sharper and more accurate predictions than regression across all modalities. Our results suggest that stochastic conditional generation of VFM features offers a promising and scalable foundation for future world models.
Abstract (translated)
从部分观测数据进行预测是世界建模的核心。许多近期的方法通过图像来表示世界，并将预测简化为随机视频生成任务。尽管这些方法在现实感和视觉保真度方面表现出色，但像素级的预测计算成本高且在很多应用场景中不够直接有用，因为它们需要将RGB信息转换成可用于决策制定的有效信号。另一种方法则是利用计算机视觉基础模型（VFMs）中的特征作为世界表示方式，并执行确定性回归以预测未来的状态。这些特征可以直接转化为语义分割、深度等行动信号，同时保持计算效率。然而，这种确定性的回归方法通过平均多个可能的未来结果来削弱了预测的准确性，因为它无法捕捉不确定性。 为了解决这个关键限制，我们引入了一种生成式预报器，在VFMs特性空间中执行自回归流匹配（autoregressive flow matching）。我们的核心见解在于：在这种空间中进行生成建模需要将VFMs特征编码到适合扩散过程的紧凑隐变量空间。研究表明这种隐变量空间比以前使用的基于PCA的方法更有效地保存信息，不仅在预测方面，在图像生成等其他应用上也是如此。我们模型产生的潜在结果可以轻松解码为多种有用且可解释的输出模式：语义分割、深度、表面法线甚至RGB。 与回归方法相比，使用相同架构和计算资源的情况下，我们的方法能够对所有模态产生更清晰准确的预测。研究表明，基于VFMs特征进行条件生成的方法可能为未来世界模型提供了有前途且具有可扩展性的基础。
URL
https://arxiv.org/abs/2512.11225
PDF
-
Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA
2025-12-11 10:47:01Pasquale De Marinis, Gennaro Vessio, Giovanna CastellanoAbstract
Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated support set. While prior research has mainly focused on improving decoders, the encoder's limited ability to extract meaningful features for unseen classes remains a key bottleneck. In this work, we introduce \textit{Take a Peek} (TaP), a simple yet effective method that enhances encoder adaptability for both FSS and cross-domain FSS (CD-FSS). TaP leverages Low-Rank Adaptation (LoRA) to fine-tune the encoder on the support set with minimal computational overhead, enabling fast adaptation to novel classes while mitigating catastrophic forgetting. Our method is model-agnostic and can be seamlessly integrated into existing FSS pipelines. Extensive experiments across multiple benchmarks--including COCO $20^i$, Pascal $5^i$, and cross-domain datasets such as DeepGlobe, ISIC, and Chest X-ray--demonstrate that TaP consistently improves segmentation performance across diverse models and shot settings. Notably, TaP delivers significant gains in complex multi-class scenarios, highlighting its practical effectiveness in realistic settings. A rank sensitivity analysis also shows that strong performance can be achieved even with low-rank adaptations, ensuring computational efficiency. By addressing a critical limitation in FSS--the encoder's generalization to novel classes--TaP paves the way toward more robust, efficient, and generalizable segmentation systems. The code is available at this https URL.
Abstract (translated)
少样本语义分割（FSS）的目标是使用仅有的少量标注支持集，在查询图像中对新类别进行分割。尽管先前的研究主要集中在改进解码器上，但编码器提取未见过类别的有意义特征的能力有限仍然是一个关键瓶颈。在这项工作中，我们引入了“Take a Peek”（TaP），这是一种简单而有效的方法，用于增强FSS和跨域少样本语义分割（CD-FSS）中编码器的适应性。TaP利用低秩适配（LoRA）在支持集上微调编码器，并且计算开销极小，从而能够快速适应新类别同时减轻灾难性遗忘问题。我们的方法是模型无关的，并可以无缝地集成到现有的FSS流程中。 我们在多个基准测试数据集上的大量实验——包括COCO 20i、Pascal 5i和跨域数据集如DeepGlobe、ISIC和胸部X光片，证明了TaP能够显著提升各种模型在不同样本设置下的分割性能。特别地，在复杂的多类别场景中，TaP表现出明显的改进效果，突显其在实际环境中的实用性和有效性。 通过秩敏感性分析也表明，即使使用低秩适配也能实现强大的性能，确保计算效率。通过解决FSS的一个关键限制——编码器对新类别的泛化能力不足的问题，TaP为更加稳健、高效且具有一般性的分割系统铺平了道路。代码可在以下网址获取：[提供链接]
URL
https://arxiv.org/abs/2512.10521
PDF
-
Hybrid Transformer-Mamba Architecture for Weakly Supervised Volumetric Medical Segmentation
2025-12-11 07:09:32Yiheng Lyu, Lian Xu, Mohammed Bennamoun, Farid Boussaid, Coen Arrow, Girish DwivediAbstract
Weakly supervised semantic segmentation offers a label-efficient solution to train segmentation models for volumetric medical imaging. However, existing approaches often rely on 2D encoders that neglect the inherent volumetric nature of the data. We propose TranSamba, a hybrid Transformer-Mamba architecture designed to capture 3D context for weakly supervised volumetric medical segmentation. TranSamba augments a standard Vision Transformer backbone with Cross-Plane Mamba blocks, which leverage the linear complexity of state space models for efficient information exchange across neighboring slices. The information exchange enhances the pairwise self-attention within slices computed by the Transformer blocks, directly contributing to the attention maps for object localization. TranSamba achieves effective volumetric modeling with time complexity that scales linearly with the input volume depth and maintains constant memory usage for batch processing. Extensive experiments on three datasets demonstrate that TranSamba establishes new state-of-the-art performance, consistently outperforming existing methods across diverse modalities and pathologies. Our source code and trained models are openly accessible at: this https URL.
Abstract (translated)
弱监督语义分割为训练体积医学影像的分割模型提供了一种标签高效的解决方案。然而，现有方法通常依赖于二维编码器，忽视了数据本身的三维特性。我们提出了一种混合Transformer-Mamba架构——TranSamba，专门用于捕捉弱监督体积医学分割中的三维上下文信息。TranSamba在标准视觉变压器主干网络的基础上增加了Cross-Plane Mamba块，利用状态空间模型的线性复杂度来实现相邻切片之间高效的信息交换。这种信息交换增强了由Transformer块计算出的片内成对自注意力机制，直接贡献于目标定位的注意图中。 TranSamba能够有效地建模体积数据，并且时间复杂度随着输入体深度呈线性增长，同时保持了批量处理中的常量内存使用率。在三个数据集上的广泛实验表明，TranSamba建立了新的最先进技术性能，在不同模式和病理条件下始终优于现有方法。 我们的源代码和训练模型可在以下网址公开访问：[此处插入实际URL]。
URL
https://arxiv.org/abs/2512.10353
PDF
-
ConStruct: Structural Distillation of Foundation Models for Prototype-Based Weakly Supervised Histopathology Segmentation
2025-12-11 06:08:29Khang Le (equal contribution), Ha Thach (equal contribution), Anh M. Vu (equal contribution), Trang T. K. Vo, Han H. Huynh, David Yang, Minh H. N. Le, Thanh-Huy Nguyen, Akash Awasthi, Chandra Mohan, Zhu Han, Hien Van NguyenAbstract
Weakly supervised semantic segmentation (WSSS) in histopathology relies heavily on classification backbones, yet these models often localize only the most discriminative regions and struggle to capture the full spatial extent of tissue structures. Vision-language models such as CONCH offer rich semantic alignment and morphology-aware representations, while modern segmentation backbones like SegFormer preserve fine-grained spatial cues. However, combining these complementary strengths remains challenging, especially under weak supervision and without dense annotations. We propose a prototype learning framework for WSSS in histopathological images that integrates morphology-aware representations from CONCH, multi-scale structural cues from SegFormer, and text-guided semantic alignment to produce prototypes that are simultaneously semantically discriminative and spatially coherent. To effectively leverage these heterogeneous sources, we introduce text-guided prototype initialization that incorporates pathology descriptions to generate more complete and semantically accurate pseudo-masks. A structural distillation mechanism transfers spatial knowledge from SegFormer to preserve fine-grained morphological patterns and local tissue boundaries during prototype learning. Our approach produces high-quality pseudo masks without pixel-level annotations, improves localization completeness, and enhances semantic consistency across tissue types. Experiments on BCSS-WSSS datasets demonstrate that our prototype learning framework outperforms existing WSSS methods while remaining computationally efficient through frozen foundation model backbones and lightweight trainable adapters.
Abstract (translated)
在组织病理学中，弱监督语义分割（WSSS）主要依赖于分类骨干模型。然而，这些模型通常只能定位最具判别力的区域，并且难以捕捉到组织结构的整体空间范围。视觉-语言模型如CONCH提供了丰富的语义对齐和形态感知表示，而现代分割骨架如SegFormer则保留了精细的空间线索。但是，在弱监督条件下以及缺乏密集注释的情况下，将这些互补优势结合在一起仍然存在挑战。 我们提出了一种用于组织病理图像WSSS的原型学习框架，该框架整合了来自CONCH的形态感知表示、SegFormer的多尺度结构提示和文本引导语义对齐，以生成同时具有判别性和空间一致性的原型。为了有效利用这些异质资源，我们引入了基于病理描述的文本引导原型初始化方法，从而生成更加完整且语义准确的伪掩膜（pseudo-masks）。此外，一种结构蒸馏机制从SegFormer中传输空间知识，在原型学习过程中保留细粒度形态模式和局部组织边界。我们的方法能够在没有像素级注释的情况下生成高质量的伪掩膜，提高定位完整性，并增强不同组织类型之间的语义一致性。 在BCSS-WSSS数据集上的实验表明，与现有的WSSS方法相比，我们提出的原型学习框架不仅性能更优，而且由于冻结了基础模型骨干和轻量可训练适配器的应用，使其计算效率更高。
URL
https://arxiv.org/abs/2512.10316
PDF
-
DualProtoSeg: Simple and Efficient Design with Text- and Image-Guided Prototype Learning for Weakly Supervised Histopathology Image Segmentation
2025-12-11 06:03:28Anh M. Vu (equal contribution), Khang P. Le (equal contribution), Trang T. K. Vo (equal contribution), Ha Thach, Huy Hung Nguyen, David Yang, Han H. Huynh, Quynh Nguyen, Tuan M. Pham, Tuan-Anh Le, Minh H. N. Le, Thanh-Huy Nguyen, Akash Awasthi, Chandra Mohan, Zhu Han, Hien Van NguyenAbstract
Weakly supervised semantic segmentation (WSSS) in histopathology seeks to reduce annotation cost by learning from image-level labels, yet it remains limited by inter-class homogeneity, intra-class heterogeneity, and the region-shrinkage effect of CAM-based supervision. We propose a simple and effective prototype-driven framework that leverages vision-language alignment to improve region discovery under weak supervision. Our method integrates CoOp-style learnable prompt tuning to generate text-based prototypes and combines them with learnable image prototypes, forming a dual-modal prototype bank that captures both semantic and appearance cues. To address oversmoothing in ViT representations, we incorporate a multi-scale pyramid module that enhances spatial precision and improves localization quality. Experiments on the BCSS-WSSS benchmark show that our approach surpasses existing state-of-the-art methods, and detailed analyses demonstrate the benefits of text description diversity, context length, and the complementary behavior of text and image prototypes. These results highlight the effectiveness of jointly leveraging textual semantics and visual prototype learning for WSSS in digital pathology.
Abstract (translated)
弱监督语义分割（WSSS）在组织病理学中的目标是通过从图像级别标签学习来减少标注成本，但目前仍受限于类别间的同质性、类别内的异质性以及基于类激活映射（CAM）的监督导致的区域缩小效应。我们提出了一种简单而有效的原型驱动框架，该框架利用视觉-语言对齐以在弱监督下改进区域发现过程。我们的方法整合了CoOp风格的学习提示调整技术来生成文本基元，并将它们与可学习的图像基元相结合，形成了一个双模态基元库，能够捕捉语义和外观线索。为了缓解ViT表示中的过度平滑问题，我们引入了一个多尺度金字塔模块，以增强空间精度并提高定位质量。 在BCSS-WSSS基准上的实验表明，我们的方法超越了现有的最先进技术，并且详细的分析展示了文本描述多样性、上下文长度以及文本与图像基元互补行为的益处。这些结果突显了联合利用文字语义和视觉原型学习对于数字病理学中WSSS的有效性。
URL
https://arxiv.org/abs/2512.10314
PDF
-
NordFKB: a fine-grained benchmark dataset for geospatial AI in Norway
2025-12-10 18:47:25Sander Riis{\o}en Jyhne, Aditya Gupta, Ben Worsley, Marianne Andersen, Ivar Oveland, Alexander Salveson NossumAbstract
We present NordFKB, a fine-grained benchmark dataset for geospatial AI in Norway, derived from the authoritative, highly accurate, national Felles KartdataBase (FKB). The dataset contains high-resolution orthophotos paired with detailed annotations for 36 semantic classes, including both per-class binary segmentation masks in GeoTIFF format and COCO-style bounding box annotations. Data is collected from seven geographically diverse areas, ensuring variation in climate, topography, and urbanization. Only tiles containing at least one annotated object are included, and training/validation splits are created through random sampling across areas to ensure representative class and context distributions. Human expert review and quality control ensures high annotation accuracy. Alongside the dataset, we release a benchmarking repository with standardized evaluation protocols and tools for semantic segmentation and object detection, enabling reproducible and comparable research. NordFKB provides a robust foundation for advancing AI methods in mapping, land administration, and spatial planning, and paves the way for future expansions in coverage, temporal scope, and data modalities.
Abstract (translated)
我们介绍了NordFKB，这是一个针对挪威地理空间AI的细粒度基准数据集，源自权威且高度准确的国家级Felles KartdataBase（FKB）。该数据集包含了高分辨率正射影像，并附有36个语义类别的详细注释，包括以GeoTIFF格式提供的每类别二值分割掩模和COCO风格的边界框标注。数据来自七个地理多样化的地区，确保了气候、地形和城市化等方面的多样性。只有包含至少一个已标注对象的数据块被纳入，并通过跨区域随机采样创建训练/验证拆分，以保证语义类和上下文分布的一致性。人工专家审查和质量控制确保了注释的准确性。 除了数据集之外，我们还发布了一个基准测试仓库，提供了用于语义分割和目标检测的标准评估协议和工具，从而实现可重复性和可比较性的研究。NordFKB为地图绘制、土地管理和空间规划领域的AI方法的发展提供了一个坚实的基础，并为未来扩展覆盖范围、时间跨度以及数据模式铺平了道路。
URL
https://arxiv.org/abs/2512.09913
PDF
-
SIP: Site in Pieces- A Dataset of Disaggregated Construction-Phase 3D Scans for Semantic Segmentation and Scene Understanding
2025-12-09 19:25:59Seongyong Kim, Yong Kwon ChoAbstract
Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development. LiDAR is widely used in construction because it offers advantages over camera-based systems, performing reliably in cluttered and dynamically changing conditions. Yet most public datasets for 3D perception are derived from densely fused scans with uniform sampling and complete visibility, conditions that do not reflect real construction sites. Field data are often collected as isolated single-station LiDAR views, constrained by safety requirements, limited access, and ongoing operations. These factors lead to radial density decay, fragmented geometry, and view-dependent visibility-characteristics that remain underrepresented in existing datasets. This paper presents SIP, Site in Pieces, a dataset created to reflect the practical constraints of LiDAR acquisition during construction. SIP provides indoor and outdoor scenes captured with a terrestrial LiDAR scanner and annotated at the point level using a taxonomy tailored to construction environments: A. Built Environment, B. Construction Operations, and C. Site Surroundings. The dataset includes both structural components and slender temporary objects such as scaffolding, MEP piping, and scissor lifts, where sparsity caused by occlusion and fragmented geometry make segmentation particularly challenging. The scanning protocol, annotation workflow, and quality control procedures establish a consistent foundation for the dataset. SIP is openly available with a supporting Git repository, offering adaptable class configurations that streamline adoption within modern 3D deep learning frameworks. By providing field data that retain real-world sensing characteristics, SIP enables robust benchmarking and contributes to advancing construction-oriented 3D vision tasks.
Abstract (translated)
在活跃的建筑工地中，对3D场景进行准确解释对于进度监控、安全评估和数字孪生开发至关重要。由于激光雷达（LiDAR）能够在混乱且动态变化的条件下可靠运行，它在建筑业中的应用十分广泛，而相机系统则难以满足这些条件的要求。然而，大多数用于三维感知的公开数据集都是从密集融合扫描中获得，具有均匀采样和完全可见度的特点，这并不反映真实的建筑工地情况。现场数据通常以单独的单站LiDAR视图形式收集，受安全要求、访问限制以及正在进行的操作影响。这些因素导致了径向密度衰减、几何碎片化及视点依赖性可见性的特点，在现有的数据集中显得不足。 本文介绍了一个名为SIP（Site in Pieces）的数据集，该数据集旨在反映在建筑工地中进行LiDAR采集的实际条件约束。SIP提供了使用地面激光雷达扫描仪捕捉的室内和室外场景，并且根据建筑环境的特点进行了点级别的标注：A. 建筑环境；B. 施工操作；C. 工地周围环境。该数据集包括结构组件以及细长临时对象，如脚手架、机电管道和剪式升降机，这些对象由于遮挡造成的稀疏性和几何碎片化使得分割变得特别具有挑战性。 SIP的扫描协议、标注工作流程及质量控制程序为数据集建立了一致的基础。该数据集以开源形式提供，并配有支持性的Git仓库，提供了可适应的类别配置，简化了其在现代3D深度学习框架中的应用。通过提供保留真实世界传感特性的现场数据，SIP能够实现稳健基准测试并推进面向建筑领域的三维视觉任务的发展。
URL
https://arxiv.org/abs/2512.09062
PDF
-
SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images
2025-12-09 15:42:28Kaiyu Li, Shengqi Zhang, Yupeng Deng, Zhi Wang, Deyu Meng, Xiangyong CaoAbstract
Most existing methods for training-free Open-Vocabulary Semantic Segmentation (OVSS) are based on CLIP. While these approaches have made progress, they often face challenges in precise localization or require complex pipelines to combine separate modules, especially in remote sensing scenarios where numerous dense and small targets are present. Recently, Segment Anything Model 3 (SAM 3) was proposed, unifying segmentation and recognition in a promptable framework. In this paper, we present a preliminary exploration of applying SAM 3 to the remote sensing OVSS task without any training. First, we implement a mask fusion strategy that combines the outputs from SAM 3's semantic segmentation head and the Transformer decoder (instance head). This allows us to leverage the strengths of both heads for better land coverage. Second, we utilize the presence score from the presence head to filter out categories that do not exist in the scene, reducing false positives caused by the vast vocabulary sizes and patch-level processing in geospatial scenes. We evaluate our method on extensive remote sensing datasets. Experiments show that this simple adaptation achieves promising performance, demonstrating the potential of SAM 3 for remote sensing OVSS. Our code is released at this https URL.
Abstract (translated)
大多数现有的无需训练的开放词汇语义分割（OVSS）方法都基于CLIP。尽管这些方法已经取得了一定的进步，但它们在精确定位上往往面临挑战，并且通常需要复杂的管道来结合单独的模块，尤其是在存在众多密集和小型目标的遥感场景中更是如此。最近提出了Segment Anything Model 3 (SAM 3)，它在一个可提示的框架内统一了分割和识别任务。在这篇论文中，我们展示了将SAM 3应用于无需训练的遥感OVSS任务的一个初步探索。 首先，我们实现了一种掩码融合策略，该策略结合了来自SAM 3语义分割头和Transformer解码器（实例头）的输出。这使我们可以利用两个头部的优点来更好地覆盖土地范围。 其次，我们使用存在评分从存在性头部过滤掉场景中不存在的类别，从而减少由于庞大词汇量以及地理空间场景中的补丁级处理所导致的假阳性情况。 我们在广泛的遥感数据集上评估了我们的方法。实验结果表明，这种简单的适应达到了令人鼓舞的效果，展示了SAM 3在遥感OVSS任务上的潜力。我们的代码可在[此处](https://this-url.com)获取。
URL
https://arxiv.org/abs/2512.08730
PDF
-
Instance-Aware Test-Time Segmentation for Continual Domain Shifts
2025-12-09 13:06:15Seunghwan Lee, Inyoung Jung, Hojoon Lee, Eunil Park, Sungeun HongAbstract
Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying difficulty across classes and instances. This limitation is especially problematic in semantic segmentation, where each image requires dense, multi-class predictions. We propose an approach that adaptively adjusts pseudo labels to reflect the confidence distribution within each image and dynamically balances learning toward classes most affected by domain shifts. This fine-grained, class- and instance-aware adaptation produces more reliable supervision and mitigates error accumulation throughout continual adaptation. Extensive experiments across eight CTTA and TTA scenarios, including synthetic-to-real and long-term shifts, show that our method consistently outperforms state-of-the-art techniques, setting a new standard for semantic segmentation under evolving conditions.
Abstract (translated)
持续测试时间适应（CTTA）使预训练模型能够适应不断变化的领域。现有的方法虽然提高了鲁棒性，但通常依赖于固定的或批处理级别的阈值，这无法考虑不同类别和实例之间的难度差异。这种限制在语义分割任务中尤为突出，因为每个图像都需要密集且多类别的预测。我们提出了一种自适应调整伪标签的方法，以反映每张图片内部的置信度分布，并动态平衡针对受领域变化影响最大的类别的学习过程。这种方法通过提供更可靠的监督信号并减轻连续适应过程中误差积累的问题，实现了细粒度、类别和实例感知的适应性。在八个CTTA和TTA场景下的广泛实验中（包括合成到真实以及长期的变化），我们的方法始终优于最先进的技术，在不断变化条件下进行语义分割方面设立了新标准。
URL
https://arxiv.org/abs/2512.08569
PDF
-
Query-aware Hub Prototype Learning for Few-Shot 3D Point Cloud Semantic Segmentation
2025-12-09 05:18:30YiLin Zhou, Lili Wei, Zheming Xu, Ziyi Chen, Congyan LangAbstract
Few-shot 3D point cloud semantic segmentation (FS-3DSeg) aims to segment novel classes with only a few labeled samples. However, existing metric-based prototype learning methods generate prototypes solely from the support set, without considering their relevance to query data. This often results in prototype bias, where prototypes overfit support-specific characteristics and fail to generalize to the query distribution, especially in the presence of distribution shifts, which leads to degraded segmentation performance. To address this issue, we propose a novel Query-aware Hub Prototype (QHP) learning method that explicitly models semantic correlations between support and query sets. Specifically, we propose a Hub Prototype Generation (HPG) module that constructs a bipartite graph connecting query and support points, identifies frequently linked support hubs, and generates query-relevant prototypes that better capture cross-set semantics. To further mitigate the influence of bad hubs and ambiguous prototypes near class boundaries, we introduce a Prototype Distribution Optimization (PDO) module, which employs a purity-reweighted contrastive loss to refine prototype representations by pulling bad hubs and outlier prototypes closer to their corresponding class centers. Extensive experiments on S3DIS and ScanNet demonstrate that QHP achieves substantial performance gains over state-of-the-art methods, effectively narrowing the semantic gap between prototypes and query sets in FS-3DSeg.
Abstract (translated)
少量样本的三维点云语义分割（Few-shot 3D Point Cloud Semantic Segmentation，FS-3DSeg）的目标是使用仅有的几个标记样本对新类别进行分割。然而，现有的基于度量的方法生成原型时只从支持集（support set）中提取信息，不考虑这些原型与查询数据（query data）的相关性。这通常会导致原型偏差，即原型过度拟合于支持集特有的特征，并且无法推广到查询分布上，尤其是在存在分布偏移的情况下，导致分割性能下降。为了解决这一问题，我们提出了一种新的基于查询的中心枢纽原型（Query-aware Hub Prototype, QHP）学习方法，该方法明确建模了支持集和查询集之间的语义关联。 具体来说，我们提出了一个枢纽原型生成（Hub Prototype Generation, HPG）模块，它构建了一个连接查询点和支持点的二分图，识别出经常被链接的支持中心，并生成更能捕捉跨集合语义的相关查询原型。为了进一步减轻坏中心的影响以及类边界附近模糊原型的影响，我们引入了原型分布优化（Prototype Distribution Optimization, PDO）模块，该模块采用了一种纯净度重新加权的对比损失来通过将“坏”的枢纽和离群的原型拉向它们对应的类别中心来细化原型表示。 在S3DIS和ScanNet数据集上的广泛实验表明，QHP方法相对于最先进的方法取得了显著的性能提升，并且有效地缩小了FS-3DSeg中原型与查询集合之间的语义差距。
URL
https://arxiv.org/abs/2512.08253
PDF
-
Restrictive Hierarchical Semantic Segmentation for Stratified Tooth Layer Detection
2025-12-08 19:15:08Ryan Banks, Camila Lindoni Azevedo, Hongying Tang, Yunpeng LiAbstract
Accurate understanding of anatomical structures is essential for reliably staging certain dental diseases. A way of introducing this within semantic segmentation models is by utilising hierarchy-aware methodologies. However, existing hierarchy-aware segmentation methods largely encode anatomical structure through the loss functions, providing weak and indirect supervision. We introduce a general framework that embeds an explicit anatomical hierarchy into semantic segmentation by coupling a recurrent, level-wise prediction scheme with restrictive output heads and top-down feature conditioning. At each depth of the class tree, the backbone is re-run on the original image concatenated with logits from the previous level. Child class features are conditioned using Feature-wise Linear Modulation of their parent class probabilities, to modulate child feature spaces for fine grained detection. A probabilistic composition rule enforces consistency between parent and descendant classes. Hierarchical loss combines per-level class weighted Dice and cross entropy loss and a consistency term loss, ensuring parent predictions are the sum of their children. We validate our approach on our proposed dataset, TL-pano, containing 194 panoramic radiographs with dense instance and semantic segmentation annotations, of tooth layers and alveolar bone. Utilising UNet and HRNet as donor models across a 5-fold cross validation scheme, the hierarchical variants consistently increase IoU, Dice, and recall, particularly for fine-grained anatomies, and produce more anatomically coherent masks. However, hierarchical variants also demonstrated increased recall over precision, implying increased false positives. The results demonstrate that explicit hierarchical structuring improves both performance and clinical plausibility, especially in low data dental imaging regimes.
Abstract (translated)
对解剖结构的准确理解对于可靠地分期某些牙科疾病至关重要。在语义分割模型中引入这一要素的一种方法是利用层次感知的方法论。然而，现有的层次感知分割方法大多通过损失函数来编码解剖结构，提供的是弱且间接的监督。我们介绍了一种通用框架，该框架将明确的解剖层次嵌入到语义分割中，通过结合递归、级联预测方案和限制性输出头以及自顶向下的特征调节实现这一目标。 在类别树的每个深度上，骨干网络都会在原始图像与前一层的logits（未标准化分数）串联后重新运行。子类别的特征通过对其父类概率进行逐通道线性调制来调节其子类特征空间，以促进细粒度检测。一种概率组合规则确保了父级和后代类别之间的连贯性。层次损失结合了每个级别的加权Dice损失、交叉熵损失以及一致性术语损失，确保父预测是其子项的总和。 我们在提出的TL-pano数据集上验证了我们的方法，该数据集包含194张全景X光片，带有密集实例和语义分割注释，包括牙齿层和牙槽骨。我们使用UNet和HRNet作为供体模型，并通过五折交叉验证方案进行实验。层次变种在所有IoU、Dice以及召回率上持续提高，特别是在细粒度解剖结构方面，并产生更符合解剖学的掩码。然而，层次变种也显示出了更高的召回率而不仅仅是精度，暗示了更多的假阳性。 结果表明，在数据量较少的牙科影像模式下，显式的层次结构能够显著改善性能和临床合理性。
URL
https://arxiv.org/abs/2512.07984
PDF
-
Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentation
2025-12-08 10:00:36Qiming Huang, Hao Ai, Jianbo JiaoAbstract
Benefiting from the inductive biases learned from large-scale datasets, open-vocabulary semantic segmentation (OVSS) leverages the power of vision-language models, such as CLIP, to achieve remarkable progress without requiring task-specific training. However, due to CLIP's pre-training nature on image-text pairs, it tends to focus on global semantic alignment, resulting in suboptimal performance when associating fine-grained visual regions with text. This leads to noisy and inconsistent predictions, particularly in local areas. We attribute this to a dispersed bias stemming from its contrastive training paradigm, which is difficult to alleviate using CLIP features alone. To address this, we propose a structure-aware feature rectification approach that incorporates instance-specific priors derived directly from the image. Specifically, we construct a region adjacency graph (RAG) based on low-level features (e.g., colour and texture) to capture local structural relationships and use it to refine CLIP features by enhancing local discrimination. Extensive experiments show that our method effectively suppresses segmentation noise, improves region-level consistency, and achieves strong performance on multiple open-vocabulary segmentation benchmarks.
Abstract (translated)
得益于从大规模数据集中学习到的归纳偏差，开放词汇语义分割（OVSS）利用了视觉-语言模型（如CLIP）的强大功能，在无需特定任务训练的情况下取得了显著进展。然而，由于CLIP在图像文本对上的预训练特性，它倾向于关注全局语义一致性，这导致在将细粒度的视觉区域与文本关联时表现不佳。这进而造成了局部区域预测中的噪声和不一致问题。我们将其归因于其对比学习范式带来的分散偏差，仅使用CLIP特征难以解决这一问题。 为了应对这一挑战，我们提出了一种基于结构感知的特征修正方法，该方法结合了直接从图像中提取的实例特定先验知识。具体而言，我们基于低级视觉特征（如颜色和纹理）构建了一个区域邻接图（RAG），以捕捉局部结构关系，并利用它来通过增强局部辨别能力来优化CLIP特征。 广泛的实验表明，我们的方法有效地抑制了分割中的噪声，提高了区域级别的一致性，并在多个开放词汇语义分割基准测试中取得了优异的性能。
URL
https://arxiv.org/abs/2512.07360
PDF
-
Generalized Referring Expression Segmentation on Aerial Photos
2025-12-08 09:25:59Lu\'is Marnoto, Alexandre Bernardino, Bruno MartinsAbstract
Referring expression segmentation is a fundamental task in computer vision that integrates natural language understanding with precise visual localization of target regions. Considering aerial imagery (e.g., modern aerial photos collected through drones, historical photos from aerial archives, high-resolution satellite imagery, etc.) presents unique challenges because spatial resolution varies widely across datasets, the use of color is not consistent, targets often shrink to only a few pixels, and scenes contain very high object densities and objects with partial occlusions. This work presents Aerial-D, a new large-scale referring expression segmentation dataset for aerial imagery, comprising 37,288 images with 1,522,523 referring expressions that cover 259,709 annotated targets, spanning across individual object instances, groups of instances, and semantic regions covering 21 distinct classes that range from vehicles and infrastructure to land coverage types. The dataset was constructed through a fully automatic pipeline that combines systematic rule-based expression generation with a Large Language Model (LLM) enhancement procedure that enriched both the linguistic variety and the focus on visual details within the referring expressions. Filters were additionally used to simulate historic imaging conditions for each scene. We adopted the RSRefSeg architecture, and trained models on Aerial-D together with prior aerial datasets, yielding unified instance and semantic segmentation from text for both modern and historical images. Results show that the combined training achieves competitive performance on contemporary benchmarks, while maintaining strong accuracy under monochrome, sepia, and grainy degradations that appear in archival aerial photography. The dataset, trained models, and complete software pipeline are publicly available at this https URL .
Abstract (translated)
参考表达分割是计算机视觉中的一个基础任务，它将自然语言理解与目标区域的精确视觉定位相结合。考虑到空中图像（例如通过无人机收集的现代航拍照片、历史档案中的照片、高分辨率卫星图像等）带来了独特的挑战，因为这些数据集的空间分辨率变化很大，颜色使用不一致，目标通常缩小到只有几个像素，并且场景包含非常高的物体密度和部分遮挡的物体。这项工作介绍了一个新的大规模参考表达分割数据集Aerial-D，该数据集专门针对空中图像设计，包括37,288张图片、1,522,523个参考表达式，这些表达覆盖了259,709个标注的目标，涵盖单个对象实例、一组实例以及21种不同的语义区域类别，从车辆和基础设施到土地覆盖类型。该数据集是通过一个全自动流程构建的，结合系统规则生成参考表达，并使用大型语言模型（LLM）增强程序来丰富参考表达的语言多样性并强调视觉细节中的关注点。此外还采用了过滤器模拟每个场景的历史成像条件。 我们采用RSRefSeg架构，在Aerial-D和先前的空中图像数据集上联合训练了模型，从而为现代和历史图像从文本中实现了统一的对象实例和语义分割。结果表明，组合训练在当代基准测试中取得了具有竞争力的表现，并且在黑白、棕褐色和颗粒状退化等历史航空摄影中的图像条件下仍保持了强大的准确性。该数据集、经过训练的模型以及完整的软件流程均可通过此链接公开获取：[在此插入实际URL]。
URL
https://arxiv.org/abs/2512.07338
PDF
-
Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues
2025-12-07 22:52:53Tuan-Anh Vu, Hai Nguyen-Truong, Ziqiang Zheng, Binh-Son Hua, Qing Guo, Ivor Tsang, Sai-Kit YeungAbstract
Glass is a prevalent material among solid objects in everyday life, yet segmentation methods struggle to distinguish it from opaque materials due to its transparency and reflection. While it is known that human perception relies on boundary and reflective-object features to distinguish glass objects, the existing literature has not yet sufficiently captured both properties when handling transparent objects. Hence, we propose incorporating both of these powerful visual cues via the Boundary Feature Enhancement and Reflection Feature Enhancement modules in a mutually beneficial way. Our proposed framework, TransCues, is a pyramidal transformer encoder-decoder architecture to segment transparent objects. We empirically show that these two modules can be used together effectively, improving overall performance across various benchmark datasets, including glass object semantic segmentation, mirror object semantic segmentation, and generic segmentation datasets. Our method outperforms the state-of-the-art by a large margin, achieving +4.2% mIoU on Trans10K-v2, +5.6% mIoU on MSD, +10.1% mIoU on RGBD-Mirror, +13.1% mIoU on TROSD, and +8.3% mIoU on Stanford2D3D, showing the effectiveness of our method against glass objects.
Abstract (translated)
玻璃是一种在日常生活中常见的固体材料，但由于其透明性和反射性，现有的分割方法难以将其与不透明材料区分开来。虽然已知人类感知依赖于边界特征和反射物体特征来区分玻璃物体，但现有文献尚未充分捕捉这些属性以处理透明物体。因此，我们提出通过边界特征增强模块（Boundary Feature Enhancement）和反射特征增强模块（Reflection Feature Enhancement）在相互促进的方式中引入这两种强大的视觉线索。 我们的方法TransCues采用了一种金字塔式变换器编码-解码架构来分割透明对象。实验证明了这两个模块可以有效结合使用，从而提高了各种基准数据集上的整体性能，包括玻璃物体语义分割、镜子物体语义分割以及通用的分割数据集。在Trans10K-v2上我们的方法比当前最佳水平高出4.2% mIoU，在MSD上高出5.6%，在RGBD-Mirror上高出10.1%，在TROSD上高出13.1%，在Stanford2D3D上高出8.3%，证明了我们对玻璃物体分割方法的有效性。
URL
https://arxiv.org/abs/2512.07034
PDF
-
Selective Masking based Self-Supervised Learning for Image Semantic Segmentation
2025-12-07 20:21:26Yuemin Wang, Ian StavnessAbstract
This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked image modelling pretraining methods. The proposed selective masking method selectively masks image patches with the highest reconstruction loss by breaking the image reconstruction pretraining into iterative steps to leverage the trained model's knowledge. We show on two general datasets (Pascal VOC and Cityscapes) and two weed segmentation datasets (Nassar 2020 and Sugarbeets 2016) that our proposed selective masking method outperforms the traditional random masking method and supervised ImageNet pretraining on downstream segmentation accuracy by 2.9% for general datasets and 2.5% for weed segmentation datasets. Furthermore, we found that our selective masking method significantly improves accuracy for the lowest-performing classes. Lastly, we show that using the same pretraining and downstream dataset yields the best result for low-budget self-supervised pretraining. Our proposed Selective Masking Image Reconstruction method provides an effective and practical solution to improve end-to-end semantic segmentation workflows, especially for scenarios that require limited model capacity to meet inference speed and computational resource requirements.
Abstract (translated)
本文提出了一种新颖的自监督学习方法，用于语义分割任务，采用选择性掩码图像重建作为预训练任务。我们的方法用选择性掩码替代了大多数掩码图像建模预训练方法中使用的随机掩码增强技术。所提出的这种方法通过将图像重构预训练分解为迭代步骤来选择性地对具有最高重构损失的图像块进行掩码，从而利用已训练模型的知识。 我们在两个通用数据集（Pascal VOC 和 Cityscapes）以及两个杂草分割数据集（Nassar 2020 和 Sugarbeets 2016）上进行了实验，结果表明我们的选择性掩码方法在下游分割精度方面优于传统的随机掩码方法和监督的ImageNet预训练：对于通用数据集提高了2.9%，对于杂草分割数据集提高了2.5%。 此外，我们发现选择性掩码方法显著提升了表现最差类别（即那些分类准确性最低的数据）的准确率。最后，我们还证明了使用相同的预训练和下游数据集可以为低预算自监督预训练提供最佳结果。 我们的选择性掩码图像重建方法为改进端到端语义分割工作流程提供了有效且实用的解决方案，特别是在需要有限模型容量以满足推理速度和计算资源要求的情况下。
URL
https://arxiv.org/abs/2512.06981
PDF
-
Balanced Learning for Domain Adaptive Semantic Segmentation
2025-12-07 15:21:22Wangkai Li, Rui Sun, Bohao Liao, Zhaoyang Li, Tianzhu ZhangAbstract
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Despite the effectiveness of self-training techniques in UDA, they struggle to learn each class in a balanced manner due to inherent class imbalance and distribution shift in both data and label space between domains. To address this issue, we propose Balanced Learning for Domain Adaptation (BLDA), a novel approach to directly assess and alleviate class bias without requiring prior knowledge about the distribution shift. First, we identify over-predicted and under-predicted classes by analyzing the distribution of predicted logits. Subsequently, we introduce a post-hoc approach to align the logits distributions across different classes using shared anchor distributions. To further consider the network's need to generate unbiased pseudo-labels during self-training, we estimate logits distributions online and incorporate logits correction terms into the loss function. Moreover, we leverage the resulting cumulative density as domain-shared structural knowledge to connect the source and target domains. Extensive experiments on two standard UDA semantic segmentation benchmarks demonstrate that BLDA consistently improves performance, especially for under-predicted classes, when integrated into various existing methods. Code is available at this https URL.
Abstract (translated)
无监督领域适应（UDA）在语义分割中的目标是将已标记的源域知识转移到未标记的目标域中。尽管自我训练技术在UDA方面非常有效，但由于不同域之间数据和标签空间中存在的类别不平衡及分布偏移问题，它们难以以平衡的方式学习每个类别。为了解决这个问题，我们提出了领域适应的均衡学习（BLDA），这是一种新颖的方法，旨在直接评估并缓解类别的偏差，而无需预先知道分布变化的情况。 首先，通过分析预测分数（logits）的分布来识别过度预测和不足预测的类别。随后，引入了一种事后方法，利用共享锚点分布对不同类别间的logits分布进行校准。此外，在自我训练过程中为了使网络能够生成无偏伪标签，我们在线估计了logits的分布，并将logits修正项纳入损失函数中。最后，利用累积密度作为领域共有的结构化知识来连接源域和目标域。 在两个标准UDA语义分割基准测试中的大量实验表明，在与各种现有方法结合使用时，BLDA能够持续提高性能，特别是在改进不足预测的类别方面表现突出。代码可以在提供的URL上获取。
URL
https://arxiv.org/abs/2512.06886
PDF
-
Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
2025-12-07 14:56:29Wangkai Li, Rui Sun, Zhaoyang Li, Tianzhu ZhangAbstract
Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous pseudo-labels, which are further amplified during training due to utilization of one-hot encoding. To address this issue, we propose ECOCSeg, a novel perspective for segmentation models that utilizes error-correcting output codes (ECOC) to create a fine-grained encoding for each class. ECOCSeg offers several advantages. First, an ECOC-based classifier is introduced, enabling model to disentangle classes into attributes and handle partial inaccurate bits, improving stability and generalization in pseudo-label learning. Second, a bit-level label denoising mechanism is developed to generate higher-quality pseudo-labels, providing adequate and robust supervision for unlabeled images. ECOCSeg can be easily integrated with existing methods and consistently demonstrates significant improvements on multiple UDA and SSL benchmarks across different segmentation architectures. Code is available at this https URL.
Abstract (translated)
伪标签学习在语义分割中广泛应用，特别是在标记稀缺的情况下，如无监督领域自适应（UDA）和半监督学习（SSL）。尽管这种方法取得了成功，但它可能会生成错误的伪标签，在训练过程中由于使用了一_hot编码而进一步放大了这些错误。为了解决这一问题，我们提出了ECOCSeg——一种新的语义分割模型视角，利用纠错输出码（ECOC）为每个类别创建精细的编码。 ECOCSeg具有几大优势： 1. 引入了一个基于ECOC的分类器，使模型能够将类别分解为属性，并处理部分不准确的信息位。这提高了伪标签学习过程中的稳定性和泛化能力。 2. 开发了一种位级标签去噪机制，用于生成更高质量的伪标签，这些标签能为未标记图像提供充分且稳健的监督。 ECOCSeg可以轻松地与现有方法结合，并在多个UDA和SSL基准测试中对不同的分割架构表现出持续显著的改进。代码可在此链接获取：[此链接应替换为你提供的具体URL]。
URL
https://arxiv.org/abs/2512.06870
PDF
