Semantic_Segmentation
-
When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression
2026-07-02 14:34:31Tien-Phat Nguyen, Ngai-Man CheungAbstract
Vision Transformers (ViTs) are strong backbones for semantic segmentation, but their computational cost limits deployment. Recent token compression methods for efficient transformer-based segmentation reduce this cost by decreasing the number of tokens. However, existing evaluations primarily focus on low-to-moderate compression, leaving their behavior under aggressive compression and corrupted inputs unclear. Meanwhile, structural pruning provides an orthogonal route to efficiency by removing redundant components in the ViT architecture, but is rarely compared to token compression under a unified protocol. To bridge this gap, we benchmark representative token compression and structural pruning methods for ViT-based semantic segmentation under matched FLOPs on ADE20K and Cityscapes, together with their common-corruption variants ADE20K-C and Cityscapes-C. Our results reveal a consistent trend on both clean and corrupted inputs: token compression is highly effective at mild reductions but degrades sharply when compression becomes severe, consistent with substantial information loss from overly aggressive token reduction. In contrast, structural pruning exhibits a smoother degradation curve and is more stable at high compression. Motivated by these findings, we study a prune-then-merge pipeline that applies moderate token compression on top of a moderately pruned backbone. At comparable FLOPs, this combined strategy consistently achieves a better accuracy-robustness trade-off at high compression, offering a practical recipe for deployment-oriented ViT segmentation. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.02237
PDF
-
UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Dataset
2026-07-02 10:50:01Yi Wang, Fan Wang, Prabin Gyawali, Ziyang Xu, Anna Klimkowska, Yixiong Jing, Wanru Yang, Filip Biljecki, Christoph Holst, Benjamin Busam, Brian Sheil, Olaf WysockiAbstract
Globally consistent semantic digital twins require centimeter-accurate and geographically transferable 3D facade segmentation. However, progress in facade parsing is limited by the lack of large-scale, standardized benchmarks for evaluating cross-domain generalization. Existing datasets are geographically narrow, semantically inconsistent, or insufficiently precise. We introduce UnderOneFacade, the largest cross-country and cross-continent 3D facade benchmark to date, comprising centimeter-accurate point clouds with hierarchical, harmonized, and architecturally grounded semantic labels totaling 2.7 billion annotated points. Through a systematic evaluation of representative point-, graph- and transformer-based architectures, we show that current methods struggle to recognize fine-grained architectural elements and degrade significantly across geographic domains, with the best models achieving only up to 33 IoU on the fine-grained LoFG3 benchmark. By combining geometric precision with standardized semantics at unprecedented scale, UnderOneFacade establishes a rigorous benchmark for developing robust and transferable 3D segmentation models. The dataset, evaluation scripts, and pretrained models will be released upon publication.
Abstract (translated)
URL
https://arxiv.org/abs/2607.02018
PDF
-
Rethinking Post-Hoc Calibration in Semantic Segmentation
2026-07-02 09:01:21Tristan Kirscher (ICube), Kim-Celine Kahl (DKFZ), Balint Kovacs (DKFZ), Maximilian R. Rokuss (DKFZ), Klaus Maier-Hein (DKFZ), Xavier Coubez (ICube), Philippe Meyer (ICube), Sylvain Faisan (ICube)Abstract
Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions. Yet modern segmentation models often remain miscalibrated. Post-hoc calibration offers a practical way to correct confidence estimates without retraining the segmentation model, but its use in dense prediction raises structural issues that are often overlooked. We study two such issues. First, adding a constant to all logits leaves the softmax probabilities unchanged, but several standard calibrators can still depend on this arbitrary offset. As a result, two logit representations encoding the same predictive distribution may yield different calibrated probabilities. We define translation-invariant (TI) calibrators as those whose outputs are unchanged under such shifts, characterize which common calibrators satisfy this property, and construct TI counterparts of shift-sensitive calibrators to isolate the effect of removing representation dependence. Second, post-hoc calibration is typically fitted by minimizing a likelihood-based objective, whereas segmentation models are trained with task-specific metrics such as Dice. This mismatch can cause calibration to alter class orderings and degrade the deployed segmentation map. We study decision-preserving calibration under argmax- and order-preservation constraints. Since enforcing these constraints collapses affine softmax calibrators to temperature scaling, we introduce class-conditional affine calibrators that can be made argmax- or order-preserving while retaining greater expressivity, allowing us to quantify the calibration-segmentation trade-off induced by decision preservation. Across natural-image and medical segmentation benchmarks, and under corruption-based covariate shift, matched comparisons show that TI variants generally improve calibration metrics, while decision-preserving variants prevent segmentation degradation and retain strong calibration performance. These results provide practical design principles for well-defined post-hoc calibration pipelines in semantic segmentation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.01902
PDF
-
Privacy-Preserving Depth-Only Open-Vocabulary 3D Semantic Segmentation Via Uncertainty-Guided Test-Time Optimization
2026-07-01 14:12:21Xuying Huang, Sicong Pan, Maren BennewitzAbstract
Privacy-preserving perception is a critical requirement for deploying 3D scene understanding systems in real-world indoor environments, yet it remains underexplored in open-vocabulary 3D semantic segmentation. Existing methods typically rely on obtaining rich semantic cues from RGB images, which may expose privacy-sensitive visual information. Depth-only 3D geometry provides a privacy-preserving alternative, but the absence of appearance-based semantic cues makes open-vocabulary predictions highly uncertain and less reliable. Under this setting, we propose to convert uncertainty into a guidance signal to identify unreliable semantic responses and use semantic priors from foundation models to regularize their refinement. We present UTTO, an uncertainty-guided test-time optimization framework for depth-only open-vocabulary 3D semantic segmentation. Without additional training, experiments on ScanNet20, ScanNet40, and ScanNet200 demonstrate that UTTO consistently improves depth-only open-vocabulary 3D segmentation and outperforms representative baselines under privacy-preserving conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2607.00978
PDF
-
LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives
2026-07-01 11:15:39Lukas Kuhn, Giuseppe Serra, Randall Balestriero, Florian BuettnerAbstract
Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time, the role of vision-language encoders has shifted: they are increasingly deployed not as zero-shot classifiers but as the frozen visual backbone of vision-language models and dense prediction systems, which consume the full grid of patch tokens rather than a single pooled embedding. We introduce LeVLJEPA, the first fully non-contrastive end-to-end vision-language pretraining method. LeVLJEPA learns through cross-modal prediction with stop-gradient targets and per-modality distributional regularization, without negatives, temperature, momentum encoder, or teacher-student schedule, and trains stably at large scale. We find that the resulting encoder provides markedly stronger dense semantic features for downstream use: as a frozen vision-language-model backbone, LeVLJEPA is the strongest of the evaluated encoders across GQA, VQAv2, and POPE under two distinct language models, and outperforms contrastive baselines on semantic segmentation, while remaining on par on global readouts such as linear probing. These results establish non-contrastive pretraining as an effective means of producing dense semantic vision features.
Abstract (translated)
URL
https://arxiv.org/abs/2607.00784
PDF
-
Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers
2026-07-01 08:02:46Cong Liu, Xiaofang Li, Simon X. YangAbstract
Vision Transformers (ViTs) commonly rely on injected positional mechanisms to address self-attention's permutation invariance. Motivated by the spatial regularities of natural images, we ask whether spatial organization can be induced from data rather than explicitly injected. Under controlled, matched from-scratch training, we propose Active Spatial Guidance (Guidance), a training-only objective that disables positional injection and applies an auxiliary 2D coordinate-regression loss to the final-layer patch tokens. The guidance head is used only during training and removed for inference; the deployed model consists of a positional-injection-free ViT encoder and the task-specific prediction module. Using DINOv3 ViT backbones, Guidance consistently improves performance on ImageNet-100 classification, ADE20K semantic segmentation, and Hypersim monocular depth estimation, outperforming strong injected baselines such as learned absolute positional embeddings and rotary positional embeddings under identical training protocols. On ImageNet-100, broader comparisons against representative injected positional designs further support Guidance's effectiveness. Guidance also improves robustness under resolution transfer, and multi-resolution training further strengthens accuracy across input sizes. Overall, our results suggest that spatial inductive bias in ViTs need not be architecturally injected, but can be shaped through training-time supervision. The code used for training and evaluation is publicly available in this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.00580
PDF
-
Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation
2026-06-30 12:57:15Ali Zia, Muhammad Umer Ramzan, Abdelwahed Khamis, Usman Ali, Abdul RehmanAbstract
Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation challenging. Most existing radar segmentation methods rely on grid-based encodings and pairwise interactions, which struggle to capture the higher-order relational structure formed by multiple radar returns from the same physical object. We introduce a unified higher-order structural alignment framework for multi-view radar segmentation. The proposed method refines radar feature representations using learnable hypergraphs to capture higher-order dependencies among spatially related responses. To ensure consistency across heterogeneous radar projections, we further align view-specific features using Unbalanced Optimal Transport (UOT), enabling correspondence-free alignment under varying measurement densities and partial observations. An adaptive attention mechanism then fuses complementary radar views while emphasising structurally informative responses under sparsity and noise. The resulting architecture learns structurally consistent representations across Range Angle (RA), Range Doppler (RD), and Angle Doppler (AD) views and is trained using supervised segmentation together with cross-view consistency regularisation. Experiments on the CARRADA and RADIal benchmarks demonstrate consistent improvements over strong radar-specific baselines, achieving 63.8% mIoU on CARRADA and 83.4% mIoU on RADIal, improving the previous best methods by +1.7 and +2.3 mIoU, respectively. These results highlight the importance of higher-order relational modelling for robust radar perception.
Abstract (translated)
URL
https://arxiv.org/abs/2606.31609
PDF
-
Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models
2026-06-30 12:51:49Nikolai R\"ohrich, Julian Glei{\ss}ner, Ahmed H. A. Ibrahim, Silvan Mertes, Tobias HuberAbstract
Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.g., dense regions or small objects in aerial or autonomous mobility data. While synthetic augmentation is an appealing solution, directly generating new labeled data risks misalignment of labels and generated pixels. Existing solutions to this problem often rely on external models, or employ coarse heuristics such as indiscriminately augmenting all foreground objects or entire backgrounds, which wastes capacity on uninformative pixels. To address this, we propose an uncertainty-guided synthetic context augmentation strategy that strictly preserves label validity and efficiently maximizes pixel informativeness per synthetic sample - no external guardrails required. Using a baseline segmenter's predictive entropy, we identify uncertain semantic regions and inpaint only the complementary visual context. When fine-tuning the segmenter on this synthetic data, we compute the loss only over the original pixels, excluding inpainted regions. This focuses learning on the unmodified, uncertain regions while presenting them in novel contexts. We demonstrate substantial mIoU gains on Cityscapes, UAVID, and BDD100K with the largest gains on rare and difficult classes such as buses, trains, or (from the aerial perspective) cars. Our results demonstrate that uncertainty-guided context augmentation is a highly effective lever to improve segmentation performance on complex datasets, with code provided at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.31603
PDF
-
HiRes: A Hierarchical Cascaded Method for Resistor Value Identification
2026-06-29 11:55:06Rama Y. AlHamidi, Aseel A. Mohamed, Mustafa A. Eltayeb, Osama Hasoneh, Mohammad ShaqfehAbstract
Accurate identification of resistor values from unconstrained images remains a challenging computer vision task due to variations in lighting, orientation, scale, and background complexity. This paper presents HiRes, a hierarchical cascaded pipeline for end-to-end resistor value identification directly from full-frame images. The approach combines object detection (YOLOv8n), semantic segmentation (UNet++ with EfficientNet-B2), and structured geometric decoding via projection along the resistor axis. To improve robustness, we incorporate geometric filtering, gap-preserving band separation, and validation against the E24 resistor series. Experiments across diverse real-world images show that HiRes achieves a detection mAP50 of 0.9906, a segmentation mIoU of 0.8444, and an end-to-end identification accuracy of 85.8% (95% CI: 78.0-91.9%), outperforming the publicly available classical baseline, CVResist, which fails to generalize beyond controlled conditions. In addition, our architecture outperforms state-of-the-art MLLMs on our challenging test set, offering a lower cost, high efficiency, and an interpretable alternative method. These results demonstrate the effectiveness of integrating learned visual representations with structured reasoning for robust resistor interpretation. Code and dataset are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.30179
PDF
-
SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring
2026-06-28 12:52:46Yufei Zhang, Chenlu Zhan, Gaoang Wang, Hongwei WangAbstract
Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches. Directly optimizing against these unreliable 2D targets forces the 3D representation to absorb multi-view contradictions, leading to severe error accumulation. To resolve this limitation, we propose SAD-GS, a framework for learning reliable 3D semantic Gaussian fields via dynamic geo-semantic anchoring. Specifically, Semantic Anchor Distillation (SAD) distills per-view visual embeddings into consensus text anchors to establish a viewpoint-invariant semantic identity. Concurrently, the Geo-Semantic Feedback Loop (GSFL) leverages the evolving 3D field to actively filter tracker anomalies and refine spatial mask assignments via a conservative three-gate update rule. Extensive evaluations on LERF-OVS, 3D-OVS, and Mip-NeRF360 show that SAD-GS consistently achieves the best overall performance in both open-vocabulary localization and semantic segmentation. These comprehensive improvements validate the effectiveness and robustness of dynamic geo-semantic anchoring for reliable 3D semantic Gaussian field learning.
Abstract (translated)
URL
https://arxiv.org/abs/2606.29376
PDF
-
Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis
2026-06-27 17:38:21Chenghao Qian, Nedko Savov, Lingdong Kong, Yeying Jin, Rui Song, Wenjing Li, Zhun Zhong, Jiaqi Ma, Gustav Markkula, Luc Van GoolAbstract
Weather synthesis aims to add weather effects to input videos while preserving scene identity, structure, and motion. The key limitation of existing methods is the lack of diversity in weather appearance and effective control over weather dynamics (e.g., temporal evolution and particle motion). Most approaches rely on text prompts, which are inherently underspecified and often fail to produce detailed weather characteristics. Additionally, general-purpose video editors optimized for clean and aesthetic outputs tend to suppress heavy weather phenomena, making dense particle effects difficult to generate. To address these, we propose a Semantic-Aware, Physics-Informed, and Geometry-Grounded framework that steers an off-the-shelf video editor to synthesize diverse global appearances and detailed particle dynamics. We factorize the synthesis into three conditional signals, so that each provides a distinct and stable source of guidance: semantics specifies what the weather should look like, dynamics governs how it evolves over time, and geometry determines where it should appear in the scene. Specifically, we introduce (1) semantic-aware appearance anchoring to establish the target appearance from scene semantics and user input; (2) physics-informed dynamic simulation to generate particle effects by simulating a Gaussian-represented particle field under gravity, wind, and turbulence; and (3) geometry-grounded video synthesis to align the simulated particles with target scene geometry and synthesize the final video. Experiments demonstrate that our method produces diverse, physically and visually realistic weather effects. Furthermore, we show that our synthesized data significantly improves the robustness of autonomous driving semantic segmentation under adverse weather conditions. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.29020
PDF
-
Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling
2026-06-26 05:54:38Qinfeng Zhu, Lei FanAbstract
Panoramic images capture the complete visual sphere in a single frame, providing spatial context unattainable by conventional cameras. Yet this completeness comes at a geometric cost: the 2-sphere cannot be faithfully mapped to the plane, and every planar representation introduces distortions that violate the assumptions underlying standard vision architectures. This survey traces the evolution of panoramic scene analysis along a methodological trajectory, from projection-based adaptation, through distortion-aware engineering, to sphere-native modeling and geometry-aware tokenization for foundation models, and argues that this evolution reflects a progressive deepening of geometric commitment rather than a simple accumulation of techniques. We organize the literature along two orthogonal dimensions: architectural design (how operators interact with spherical geometry) and training paradigm (how knowledge is transferred across domains). Covering dense prediction (semantic segmentation, depth estimation, and room layout estimation), unified multi-task understanding, open-world perception, vision-language reasoning, and dynamic video analysis, we identify a central unresolved tension: among the methods surveyed, none simultaneously delivers strict spherical equivariance and full reuse of perspective-pretrained foundation-model weights, and we argue that this is a structural rather than incidental gap. We further expose five systematic gaps in current evaluation protocols, namely the absence of spherical-area-weighted metrics, seam-consistency testing, polar-robustness stratification, cross-projection generalization, and open-world protocol standardization, and propose a six-point research roadmap toward general-purpose panoramic intelligence. The corresponding repository is publicly available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.27745
PDF
-
OctoSense: Self-Supervised Learning for Multimodal Robot Perception
2026-06-25 17:30:49Anthony Bisulco, Jeremy Wang, Kostas Daniilidis, Randall Balestriero, Pratik ChaudhariAbstract
We present OctoSense, an open-source sensor platform with stereo RGB and event cameras, LiDAR, a thermal camera, an inertial measurement unit, RTK-corrected global positioning system, and proprioception (CAN bus data from a car, and joint angles for a quadruped robot). The eponymous OctoSense dataset contains 59 hours of time-synchronized driving data across different types of environments at different times of the day, including situations with highly degraded sensors. We demonstrate multi-modal self-supervised learning using such real-world robotics data, where sensors have different representations, frequencies, latencies and noise. Our approach, a "late-fusion" masked autoencoder, (i) uses modality-specific tokenizers to account for different spatiotemporal characteristics of these sensors, and (ii) caches modality-specific tokens at inference time to process new measurements as they come. This architecture (i) is fast (6.68 ms and 112 ms on NVIDIA 5090 and Orin NX respectively, to compute the representation), (ii) performs better than existing image-only foundation models on tasks such as estimation of optical flow, depth, semantic segmentation, and ego-motion (translation, rotation, and steering angle), and (iii) predicts robustly at nighttime or in situations where sensory data is degraded. See our project page for links to the dataset, code, and supplementary videos: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.27317
PDF
-
TaskTok: Delving into Task Tokens for Task-driven Image Restoration
2026-06-25 05:20:01Hongjae Lee, Sojung Kang, Jaeseong Yu, Seung-Won JungAbstract
While traditional image restoration focuses on perceptual quality, Task-Driven Image Restoration (TDIR) aims to maximize the performance of downstream high-level vision tasks. Recent approaches leveraging generative priors have shown promise for TDIR; however, they typically suffer from computational inefficiency and potential semantic alteration by indiscriminately updating all latent tokens. In this paper, we posit that not all visual information is equally important for machine perception. Through an analysis of the latent token space, we observe that task-relevant cues are unevenly distributed across the token sequence, exhibiting index-wise specialization. This suggests that selectively refining a subset of tokens can be sufficient for task-driven objectives. Leveraging this insight, we propose TaskTok, a novel framework that selectively restores only task-relevant tokens via a learnable token switch and a lightweight token refinement module. Extensive experiments across image classification, semantic segmentation, and object detection demonstrate that TaskTok significantly enhances task performance with high computational efficiency. The source code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2606.26615
PDF
-
RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation
2026-06-25 03:52:43Shanwen Wang, Xin Sun, Sirui Wang, Xiao Xiang ZhuAbstract
Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding. However, existing OVSS methods primarily focus on modifying the CLIP attention mechanism, which still suffers from unstable local segmentation for remote sensing (RS) domain. To address these limitations, we propose RSGPNet, a training-free geometric prompting framework for RS OVSS that refines segmentation by leveraging object geometric areas and consistency constraints. Specifically, RSGPNet comprises three core modules: a Text-guided Coarse Mask module (TCM), a Geometric Re-prompting Module (GRP), and a Coarse-to-fine Consistency Verification Mechanism (CVM). TCM utilizes text prompts and the input image to construct initial coarse segmentation masks. GRP then converts these coarse masks into geometric box prompts, feeding them back into the segmentation model to generate refined masks. Finally, CVM employs consistency computation to prevent prompting from reinforcing erroneous regions. They allow the model to improve segmentation accuracy in complex areas, such as category boundaries. Extensive experiments on RS datasets demonstrate that RSGPNet significantly outperforms state-of-the-art methods across both quantitative and qualitative metrics while exhibiting excellent interpretability. The code is released at \href{this https URL}{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2606.28410
PDF
-
Learning Stable Canonical Worlds for Novel View Synthesis and Beyond
2026-06-25 03:36:03Xiaoyu Xu, Jian Zou, Sheyang Tang, Zhihua Wang, Jing Liao, Kede MaAbstract
Feed-forward Gaussian splatting (FFGS) facilitates real-time novel view synthesis, yet current methods often remain tied to view-dependent predictions. As more input views are added, they may accumulate noisy or redundant evidence instead of converging to a stable scene representation. In this paper, we introduce CanonicalGS, a feed-forward pipeline that maps cluttered multi-view observations into a stable, scene-centric representation. CanonicalGS first extracts view-centric evidence from depth, semantic features, and uncertainty estimates, and then aggregates this evidence in a canonical latent world using uncertainty-aware fusion. By emphasizing reliable observations while suppressing uncertain or redundant ones, CanonicalGS produces representations that scale more effectively for novel view synthesis and transfer to downstream visual perception tasks. Experiments show up to a $2.5$ dB improvement in peak signal-to-noise ratio for synthesizing novel views and an $11\%$ gain in semantic segmentation accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2606.23027
PDF
-
Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs
2026-06-24 11:06:22Yunhun Nam, Jongheon JeongAbstract
Vision-Language Models (VLMs) have shown strong performance in visual understanding, yet they still suffer from hallucinations, generating content that is not grounded in the image. Preference alignment is a promising approach to improve visual faithfulness, but its success depends heavily on how preference pairs are constructed. Existing methods exhibit two key limitations; (a) intervention-based methods often introduce significant deviation from the policy distribution, and (b) sampling-based methods often underuse visual information during the construction. In this paper, we propose ViPSy (Vision-driven Preference Synthesis), a framework for constructing preference data that are both policy-aligned and visually grounded. Our framework consists of two stages; in the first stage, ViPSy derives a visual cue from recurring object-level content across semantically aligned image variants, so preference construction can rely on visual information rather than language priors. In the second stage, ViPSy conditions the policy's own rollouts on this cue, allowing candidates to be guided by visually grounded content while staying close to the policy's response distribution. The resulting candidates remain close to the policy's response distribution while better leveraging visual information from the image. Experiments show that the resulting VLM, preference-aligned with ViPSy-constructed preference pairs, achieves a new state-of-the-art in hallucination mitigation. Compared with the previous state-of-the-art method, it reduces hallucination rates on AMBER and Object HalBench by 35.7% and 24.5%, respectively. The resulting model further improves on general visual grounding benchmarks, e.g., MMStar, MMVP, and CV-Bench, while also yielding gains in semantic segmentation and ImageNet linear probing, underscoring the effectiveness of our framework in enhancing the model's visual capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2606.28401
PDF
-
Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation
2026-06-24 01:31:22Xiaopei Wu, Yuenan Hou, Junkai Xu, Wenxiao Wang, Binbin Lin, Yu Li, Ping Li, Haifeng Liu, Deng Cai, Wanli OuyangAbstract
Multi-modal fusion and multi-model ensembling are prevalent in enhancing the performance of 3D semantic segmentation. Despite the impressive performance, these methods either rely on auxiliary input signals or suffer from costly computational expense. To efficaciously enhance the segmentation performance without introducing intolerable costs, we propose to transfer the rich knowledge from the multi-modal model (i.e., point clouds and images) and multiple model experts to the point-cloudbased network through knowledge distillation. Specifically, we present Information-oriented Heterogeneous Distillation (IHD) to help the uni-modal model absorb the complementary knowledge from the multi-modal teacher. We design the Information-Oriented Filtering (IOF) strategy to select informative images from the continuous image sequence for multi-modal fusion. This practice can boost the performance of the multi-modal teacher, thus benefiting the learning of the student. Besides, as opposed to vanilla model ensembling that requires the separate training of each expert, we propose Adept Snapshot Distillation (ASD). ASD treats the freely available model snapshots generated during the training phase as multiple experts, which significantly reduces the training cost for model ensembling. For each expert teacher, it only provides supervision to the student in the class where it is adept. The resulting Heterogeneous and Adept Snapshot Knowledge Distillation, dubbed HAS-KD, attains state-of-the-art results on ScanNetV2 and S3DIS datasets. HAS-KD can be seamlessly integrated into contemporary 3D segmentation algorithms and bring considerable gains without introducing extra inference burdens. The code will be made publicly available upon publication.
Abstract (translated)
URL
https://arxiv.org/abs/2606.25278
PDF
-
Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation
2026-06-23 20:02:57\"Umit Mert \c{C}a\u{g}lar, Alptekin TemizelAbstract
Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity. However, such metrics, including the widely used FID, focus on visual fidelity without reflecting downstream utility, and can diverge from human perception under perturbations that are imperceptible to human observers. In this work, we systematically evaluate Earth observation datasets alongside synthetic counterparts generated by deep generative models, comparing automatic metrics against human perception and downstream tasks. Our results reveal a stark misalignment: semantics-preserving perturbations such as rotation drastically alter metric scores while leaving human recognition unaffected, and synthetic samples that score poorly on automatic metrics achieve comparable or higher perceived realism, and can improve downstream performance when combined with real data. By benchmarking semantic segmentation models trained on mixed real-synthetic datasets, we demonstrate that quality metrics rooted in ImageNet-pretrained feature spaces are unreliable indicators for geospatial data. Our findings underscore that automatic quality evaluation of synthetic datasets should be grounded in downstream task performance and human evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2606.25128
PDF
-
Tri-Efficient Transfer Learning for Point Cloud Videos
2026-06-23 05:55:02Yiding Sun, Dongxu Zhang, Jihua Zhu, Haozhe Cheng, Zhengqiao Li, Pengcheng Li, Chaowei Fang, Yonghao Dong, Lin ChenAbstract
While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two critical limitations: prohibitive annotation costs for large-scale point cloud datasets and severe memory bottlenecks. In this paper, we aim to mine richer supervision signals from existing data rather than blindly scaling datasets. A further key principle is that the memory footprint of fine-tuning must be drastically reduced compared to full fine-tuning, which remains elusive for current PEFT techniques. Driven by these challenges, we identify three core desiderata: data-, parameter-, and memory efficiency, and present PoinTriE, a unified framework that excels along all three dimensions. For pre-training, pseudo-motion trajectories are synthesized via rigid transformations, paired with text corpora and 2D projections derived from raw point clouds. We then propose a Geometric-Motion Duality Network optimized via multimodal contrastive learning, rigid rotation prediction, and motion distribution divergence to produce dense self-supervision. During fine-tuning, we freeze the pretrained backbone and only update a lightweight Spatio-temporal Side Network built with LoRA units. Equipped with a gradient flow masking strategy, PoinTriE simultaneously reduces memory consumption and parameter overhead. Extensive experiments confirm that PoinTriE establishes new state-of-the-art results on action recognition and semantic segmentation tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2606.24175
PDF
