Semantic_Segmentation
-
Continual Segmentation under Joint Nonstationarity
2026-05-19 22:20:00Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary, Brejesh LallAbstract
Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured prediction systems, yet remains largely unexplored in prior continual learning work, which typically studies these factors in isolation. We formalize continual segmentation under coupled class, domain, and label shifts and investigate learning in heterogeneous dense prediction environments with limited annotations and abundant unlabeled data. To address instability and overfitting arising from few-shot supervision under distribution drift, we introduce gradient-adaptive stabilization, a parameter-wise regularization mechanism implemented via gradient-scaled stochastic perturbations that promotes a principled stability-plasticity tradeoff. We further leverage unlabeled data through semi-supervised learning and introduce prototype anchored supervision that validates pseudo-labels via joint confidence and prototype consistency. Together, these mechanisms enable learning under joint nonstationarity in continual segmentation. Extensive empirical evaluation across class-incremental, domain-incremental, and few-shot regimes demonstrates consistent improvements over prior methods in heterogeneous structured prediction settings. Our results expose fundamental failure modes of existing continual segmentation approaches and provide insight into learning robust dense predictors in dynamically evolving environments.
Abstract (translated)
URL
https://arxiv.org/abs/2605.20538
PDF
-
Latent Space Guided Scenario Sampling for Multimodal Segmentation Under Missing Modalities
2026-05-19 18:23:22Irem Ulku, \"O. \"Ozg\"ur Tanr{\i}\"over, Erdem Akag\"und\"uzAbstract
Multimodal semantic segmentation benefits remote sensing analysis by combining complementary information from different sensor modalities. In real-world remote sensing applications, one or more modalities may be unavailable due to sensor failures, adverse atmospheric conditions, or data acquisition problems. Even with pretrained multimodal representations and existing fine-tuning or adaptation strategies, performance may remain limited because all modality availability scenarios are typically treated as equally informative during training. In this paper, we propose a novel training strategy that learns a scenario sampling distribution directly from the pretrained latent space. Instead of relying on uniform random modality dropout, the proposed method guides fine-tuning toward more informative modality availability scenarios. More specifically, we quantify the effect of each scenario independently based on the distortion it induces in the shared latent representation. We then capture scenario relations using a radial basis function kernel and derive refined scenario scores through a regularized kernel smoothing. These scores are then converted into a probability distribution during scenario sampling for fine-tuning. We evaluate this strategy on three remote sensing image sets, namely DSTL, Potsdam, and Hunan, using CBC-SLP, CBC, and CMX backbones. The experimental results with different image sets and backbones show that our method outperforms standard fine-tuning and LoRA-based adaptation. These findings suggest that the pretrained latent representation can serve as an effective basis for sampling during missing modality fine-tuning. Code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.20372
PDF
-
WBCAtt+: Fine-Grained Pixel-Level Morphological Annotations for White Blood Cell Images
2026-05-19 11:25:25Satoshi Tsutsui, Winnie Pang, Shuting He, Bihan WenAbstract
The microscopic examination of white blood cells (WBCs) plays a fundamental role in pathology and is essential for diagnosing blood disorders such as leukemia and anemia. To support further research on WBC images, multiple datasets have been proposed. However, they mainly annotate cell categories, and lack detailed morphological characteristics that pathologists use to explain their interpretations of cells. To address this gap, we introduce WBCAtt+, a novel dataset of WBC images densely annotated with 11 morphological attributes and five pixel-level cell components. With 113k image-level labels and 10k segmentation maps, WBCAtt+ is the first to provide comprehensive annotations for WBC images. Leveraging this dataset, we provide baseline models for attribute recognition and semantic segmentation. We also design an attribute recognition model to incorporate compositional structure of cells, further improving the recognition performance. Lastly, we showcase various applications enabled by our dataset, such as explainable AI models, including counterfactual example generation. \revision{The dataset and code are publicly available\footnote{this https URL}}.
Abstract (translated)
URL
https://arxiv.org/abs/2605.19692
PDF
-
Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
2026-05-19 04:22:17Junyuan Ma, Xunzhi Xiang, Wenbin Li, Qi Fan, Yang GaoAbstract
Vision foundation models (VFMs) have achieved strong performance across various vision tasks. However, it still remains challenging to apply VFMs for cross-domain few-shot segmentation (CD-FSS), which segments objects of novel classes under domain shifts using only a few labeled exemplars. The challenge is mainly driven by two factors: (1) limited labeled exemplars per novel class relative to the scale of VFM pre-training, making the model prone to overfitting during retraining, and (2) target-domain shifts underrepresented during pre-training, inducing cross-domain inconsistency and layer-wise sensitivity. To address these issues, we propose Hierarchical Exemplar Representation Adaptation (HERA), a three-stage select-regularize-calibrate VFM-based segmentation framework that learns effectively from limited labels and adapts to novel domains without source-data retraining. We first design Hierarchical Layer Selection (HLS) to adaptively identify the most informative VFM layer using a data-dependent Exemplar Transfer Risk (ETR) computed for each candidate layer. Then, Prior-Guided Regularization (PGR) regularizes interactions on the selected representation, yielding well-structured local signals for the subsequent stage. Furthermore, Pixelwise Adaptive Calibration (PAC) combines the selected representation with the refined interaction maps to calibrate pixel-wise predictions, producing consistent masks. Together, these stages form a hierarchical select-regularize-calibrate pipeline that guides frozen VFM features in new domains while fine-tuning less than 2.7% of parameters at test time. Extensive experiments show that HERA surpasses the state of the art by more than 4.1 mIoU across multiple CD-FSS benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2605.19340
PDF
-
PRISM-SLAM: Probabilistic Ray-Grounded Inference for Scale-aware Metric SLAM
2026-05-19 02:10:04Eunsoo ImAbstract
Monocular SLAM historically suffers from scale ambiguity and tracking failure in dynamic environments. While recent vision foundation models (VFMs) provide remarkable zero-shot depth priors, naively integrating these deterministic predictions ignores predictive uncertainty and frame-to-frame scale inconsistencies. We propose PRISM-SLAM, a real-time framework that rigorously integrates VFM priors into a structured Bayesian factor graph to achieve scale-aware, metric-consistent localization and mapping. Specifically, we introduce a Plücker Ray-Distance Factor to anchor monocular observations in absolute space within a globally consistent metric coordinate system, mathematically resolving scale drift by making the metric scale Fisher-identifiable. To handle environmental dynamics, we derive an epistemic uncertainty proxy from temporal depth consistency and formulate a Dynamic Scene Uncertainty Gating (DSUG) mechanism. This soft-gating approach probabilistically down-weights dynamic distractors without incurring the heavy computational overhead associated with traditional semantic segmentation masks. By employing a multi-process architecture that asynchronously processes VFM inference and geometric tracking, PRISM-SLAM provides verified metric output at 30 FPS using solely RGB input, bridging the gap between foundation models and real-world robotic applications. Evaluated on the TUM RGB-D and 7-Scenes benchmarks, PRISM-SLAM achieves a metric $SE(3)$ Absolute Trajectory Error (ATE) nearly identical to its oracle-aligned $Sim(3)$ error. This demonstrates that our system can produce deployment-ready metric trajectories by delivering robust metric SLAM solutions without any post-hoc scale correction. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.19257
PDF
-
CosFly: Plan in the Matrix, Fly in the World
2026-05-18 21:11:18Hanxuan Chen, Xiangyue Wang, Songsheng Cheng, Ruilong Ren, Jie Zheng, Shuai Yuan, Tianle Zeng, Hanzhong Guo, Binbo Li, Kangli Wang, Ji PeiAbstract
We present CosFly, a box-structured planning and multimodal simulation pipeline for aerial tracking, together with CosFly-Track, a large-scale UAV dataset for dynamic target tracking across diverse environments including urban centers, highways, rural landscapes, forests, and coastal towns. In our current implementation on CARLA, CosFly provides a modular 7-step construction pipeline that converts complex 3D worlds into structured obstacle representations for planning, then projects the resulting trajectories back into multi-modal sensor data -- including RGB images, high-precision depth maps, and semantic segmentation masks -- paired with natural language navigation instructions. A key feature is the support for configurable fixed-FOV zoom levels (one FOV setting drawn per trajectory and held constant throughout), enabling simulation of various focal lengths through camera-intrinsic adjustments. The pipeline covers the complete workflow from 3D map export through grid simplification, pedestrian and drone trajectory planning, multi-modal rendering with 6-DOF pose annotations, quality inspection, and teacher-student caption generation. We analyze two trajectory-planning paradigms for aerial target tracking: a conventional two-stage pipeline with front-end candidate generation and backend refinement, and a direct gradient-based formulation that optimizes multiple tracking constraints in a single objective. The public CosFly-Track release contains 250 validated trajectories and approximately 100,000 rendered images with complete 6-DOF drone pose annotations (position x, y, z and orientation yaw, pitch, roll). Together, the pipeline and dataset establish a scalable foundation for aerial-ground collaborative research, supporting dynamic target tracking, UAV navigation, and multi-modal perception across diverse environments.
Abstract (translated)
URL
https://arxiv.org/abs/2605.19120
PDF
-
SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
2026-05-18 08:31:04Soyeon Yoon, Chang Wook Seo, Hyunjung ShimAbstract
Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric fidelity, and efficiency. We address this by proposing SGSoft, a unified intrinsic pipeline that (i) constructs a geodesic correspondence field on a canonical template, (ii) learns multimodal dense descriptors guided by pretrained semantic priors with this geodesic correspondence field supervision, (iii) retrieves dense correspondences in a single feed-forward pass via nearest-neighbor search in descriptor space. This formulation enables stable and topology-invariant supervision under large pose variation, structural differences, and remeshing. SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods. It also achieves near real-time inference without pre-alignment, pairwise optimization, or post-refinement. Learned descriptors can be transferred effectively to downstream tasks such as semantic segmentation and deformation transfer, establishing a scalable and deployment-ready paradigm for dense 3D correspondence.
Abstract (translated)
URL
https://arxiv.org/abs/2605.18039
PDF
-
CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization
2026-05-18 02:49:58Xiangyue Wang, Hanxuan Chen, Songsheng Cheng, Ruilong Ren, Jie Zheng, Shuai Yuan, Tianle Zeng, Hanzhong Guo, Kangli Wang, Ji PeiAbstract
Recent aerial vision-language navigation (VLN) datasets have grown rapidly, but they primarily address goal-oriented navigation to static destinations, leaving UAV visual tracking -- continuously following a moving target while maintaining visibility -- largely without dedicated training data. We introduce CosFlyTrack, a large-scale multi-modal dataset and scalable generation pipeline for UAV visual tracking in urban environments. The dataset provides approximately 12,000 expert and perturbed UAV trajectories generated from 6,000 pedestrian paths, comprising 2.4 million timesteps (approximately 334 hours) with seven aligned data channels: RGB, metric depth, semantic segmentation, six-degree-of-freedom drone pose, target state with visibility flag, bilingual (Chinese-English) instructions, and trajectory-pair metadata. To generate high-quality expert trajectories, we develop MuCO, a multi-constraint optimizer that plans directly in continuous three-dimensional space with BVH-accelerated collision and visibility queries, jointly enforcing target visibility, viewpoint quality, collision avoidance, smoothness, and kinematic feasibility, avoiding the discretization artifacts and post-hoc smoothing of grid-based planners. Fine-tuning experiments on seven vision-language models show that CosFlyTrack improves tracking performance to 78.3 to 95.6 percent SR@1 meter, a 53 to 69 percentage point gain over zero-shot baselines, supporting the dataset as a training resource for dynamic target-following agents. The dataset is publicly available at this https URL evaluation scripts and pre-trained checkpoints are hosted at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17776
PDF
-
Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework
2026-05-18 02:44:54Ziyang Liu, Hongyuan Wang, Zijian Wang, Yinxi Lu, Yunzhao Zang, Zhiqiang Yan, Qianhao NingAbstract
Physical adversarial attacks often overfit single surrogate models and optimization objectives. While ensemble attacks can mitigate this, existing methods struggle with severe gradient conflicts within restricted physical texture spaces, significantly degrading cross-model transferability. To bridge this gap, this paper proposes a Joint Multi-Objective and Multi-Model Optimization Framework (JMOF) that leverages quantitative similarity analysis to select the optimal surrogate model ensemble. Within JMOF, a dual-level mechanism jointly suppresses prediction outputs and flattens intermediate feature distributions, balancing attack efficiency with deep generalization. Additionally, an Orthogonal Gradient Alignment (OGA) strategy resolves cross-model gradient conflicts, transforming mutually repulsive gradients into synergistic optimization directions. Extensive simulated and real-world experiments demonstrate that JMOF outperforms state-of-the-art baselines against diverse black-box detectors. Crucially, JMOF exhibits substantial cross-vision-task generalization, generating attacks capable of simultaneously deceiving object detection and semantic segmentation or monocular depth estimation models. This research advances the generalization limits of physical adversarial attacks, providing a robust framework for evaluating visual AI vulnerabilities in real-world deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17772
PDF
-
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
2026-05-18 01:52:12Ronyu Zhang, Aosong Cheng, Gaole Dai, Yulin Luo, Jiaming Liu, Li Du, Huanrui Yang, Dan Wang, Leyuan Fang, Yuan Du, Shanghang ZhangAbstract
Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error accumulation and catastrophic forgetting. Drawing inspiration from the process of decoupling shape and texture in the human visual system, we introduce MoASE, a plug-in mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture using Activation Sparsity Experts with Spatial Differentiable Dropout, forming complementary high- and low-activation pathways, while high- and low-rank bottlenecks diversify representations. The Activation Sparsity Gate produces input-adaptive SDD thresholds for precise token selection, and the Domain-Aware Router assigns per-sample expert weights using texture-sensitive cues. To curb confirmation bias on unlabeled streams and stabilize supervision, we then introduce Domain-Adaptive On-Policy Distillation to constitute MoASE++, with an EMA-anchored on-policy reverse KL distillation and an augmentation policy conditioned on entropy and confidence that aligns predictions across the same views and improves the robustness-plasticity balance. Extensive experiments on classification (CIFAR-10/100-C, ImageNet-C) and semantic segmentation (Cityscapes->ACDC) demonstrate consistent state-of-the-art performance, offering a principled, controllable approach to continual adaptation in dynamic visual environments.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17743
PDF
-
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
2026-05-17 19:51:32Abderrahmene Boudiaf, Irfan Hussain, Sajid JavedAbstract
Here's a trimmed version under 1920 characters: Open-vocabulary segmentation models such as SAM3 achieve strong performance through concept-level text prompting, yet degrade when the target class is visually underrepresented in pretraining data or when its appearance departs from canonical depictions. Text prompts provide no spatial signal to resolve such ambiguity. We present SegRAG, a training-free retrieval-augmented segmentation framework that grounds SAM3 with spatially precise, class-specific point prompts derived from a curated DINOv3 feature bank. During an offline stage, patch-level descriptors are extracted from annotated reference images using a frozen DINOv3 ViT-L/16 backbone and filtered by Intra-Class Cohesion Distillation (ICCD), retaining only prototypes that reliably retrieve within-class foreground. At inference, Topographic Similarity Grounding (TSG) computes a cosine-similarity landscape between the query image and retrieved prototypes, identifies spatially coherent high-confidence regions via connected-component analysis, and extracts peak locations through non-maximum suppression. These point prompts are delivered to SAM3 alongside the class-name text in a single joint grounding pass, enabling the mask decoder to resolve semantic intent and spatial evidence together. SegRAG requires no task-specific training and no synthetic data. On four open-vocabulary benchmarks it achieves consistent gains over the SAM3 text-only baseline, with improvements of up to +3.92 mIoU on LVIS. On AgML agricultural benchmarks representing a zero-shot domain transfer setting, it raises mean IoU from 25.27 to 59.24 (+33.97) and recovers individual classes from zero to over 95 mIoU. Ablation studies confirm that ICCD, TSG, and joint prompting each contribute independently and compound when combined. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17630
PDF
-
Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning
2026-05-17 19:43:05Miquel Mart\'i i Rabad\'an, Alessandro Pieropan, Hossein Azizpour, Atsuto MakiAbstract
We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on partially labeled datasets with differently structured output tasks. Specifically, we use the popular FixMatch method for invariant semi-supervised learning and its equivariant extension Dense FixMatch. We evaluate their performance on the Cityscapes and BDD100K datasets in the context of the prevalent object detection and semantic segmentation tasks in computer vision. We consider varying sizes of the subsets annotated for each task and different overlaps among them. Our results for both invariant and equivariant semi-supervised learning outperform supervised baselines in most situations, with the most significant improvements observed when fewer labeled samples are available for a task and generally better results for the latter approach. Our study suggests that invariant/equivariant learning is a promising general direction for multi-task learning from limited labeled data.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17624
PDF
-
HyperVision: A Channel-Adaptive Ground-Based Hyperspectral Vision Pre-trained Backbone
2026-05-17 06:50:06Guanyiman Fu, Jingtao Li, Zihang Cheng, Zhuanfeng Li, Diqi Chen, Yan Xu, Fengchao Xiong, Jianfeng Lu, Jun ZhouAbstract
While hyperspectral imaging provides rich spatial-spectral information across hundreds of narrow wavelength bands for precise material identification, ground-based hyperspectral pre-trained backbones remain absent, constrained by varying spectral configurations across sensors, the scarcity and inconsistency of labels, and the limited scale and scene diversity of existing datasets. To address these challenges and enable universal perception, we propose HyperVision, the first ground-based hyperspectral pre-trained backbone. First, to handle varying spectral configurations, HyperVision adopts a channel-adaptive dynamic embedding mechanism to map heterogeneous inputs into a unified token space. Second, to address the scarcity and inconsistency of labels, we introduce a multi-source pseudo-labeling method that fuses semantic representations from both spatial structures generated by SAM2 and fine-grained spectral material information extracted by HyperFree. Third, to compensate for limited dataset scale and enrich scene diversity, a cross-modal knowledge distillation mechanism is utilized to transfer rich semantic representations from a pre-trained RGB vision model to our hyperspectral backbone. Pre-trained on a collection of 15k images from 26 diverse ground-based datasets, HyperVision demonstrates exceptional generalization. Requiring only efficient head-only adaptation without adjusting backbone parameters, it achieves state-of-the-art performance compared to task-specific methods across three downstream tasks under varying sensor configurations, yielding up to a 16.3% relative improvement in hyperspectral semantic segmentation $\mathrm{Acc}_{\mathrm{M}}$, a 2.1% relative gain in object tracking AUC, and a 35.5% reduction in salient object detection MAE. The source code and pre-trained model will be publicly available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2605.17286
PDF
-
OPTNet: Ordering Point Transformer Network for Post-disaster 3D Semantic Segmentation
2026-05-16 23:53:25Nhut Le, Ehsan Karimi, Maryam RahnemoonfarAbstract
Post-disaster damage assessment requires rapid and accurate semantic segmentation of 3D point clouds to identify critical infrastructure such as damaged buildings and roads. Early Point Transformers (e.g., PTv1, PTv2) relied on computationally expensive neighbor searching (k-NN) and Farthest Point Sampling (FPS). To improve efficiency, recent architectures like Point Transformer V3 (PTv3) adopted static serialization methods, such as Hilbert curves or Z-order, to organize unstructured points for window-based attention. However, these fixed orderings are not optimal for capturing the complex geometry of disaster scenes. In this paper, we propose OPTNet (Ordering Point Transformer Network), which introduces a learnable Point Sorter module. OPTNet utilizes a self-supervised ordering loss to dynamically predict an optimal permutation that maximizes the locality of the attention mechanism. We evaluate our method on the 3DAeroRelief dataset, significantly outperforming state-of-the-art baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17197
PDF
-
Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation
2026-05-16 19:58:41Bin Yang, Alexandru Paul ConduracheAbstract
Annotating large-scale LiDAR point clouds for 3D semantic segmentation is costly and time-consuming, which motivates the use of semi-supervised learning (SemiSL). Standard LiDAR SemiSL methods typically adopt a two-step training paradigm, where pseudo-labels are separately generated from a single distillation source, either from the same or another LiDAR representation. Such supervision relies on a unique source of pseudo-labels, which can reinforce confirmation bias and propagate errors during training, ultimately limiting performance. To address this challenge, we introduce CoLLiS, a novel framework that leverages Collaborative Learning for LiDAR Semi-supervised segmentation. Unlike prior paradigms with decoupled pseudo-labeling and training phases, CoLLiS trains multiple representations collaboratively in a single step by treating them as coequal students. Each student is adaptively distilled from multiple representations, while inter-student disparities are monitored online to resolve contradictory supervision and effectively mitigate confirmation bias. Extensive experiments on three datasets demonstrate that CoLLiS consistently outperforms state-of-the-art LiDAR SemiSL methods, with particularly strong gains in low-label regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17135
PDF
-
A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
2026-05-16 19:37:41Minhas Kamal, Hiranya Garbha Kumar, Balakrishnan PrabhakaranAbstract
Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine learning based methodologies. To combat these issues, diverse strategies have been developed, including converting to a format that has orderliness, extracting local geometry, and permutation-invariant or self-attention-based processing. In this paper, our focus is directed towards deep learning models for three fundamental tasks in 3D vision: point cloud classification, part segmentation, and semantic segmentation. We begin by formally defining point cloud data, followed by an in-depth discussion on its structural characteristics. Then, we categorize notable works based on their backbone structure and evaluate their performance on popular benchmarks. Beyond empirical comparison, we offer insights into architectural innovations and limitations. We also outline open challenges and promising future directions for 3D point cloud understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17131
PDF
-
1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?
2026-05-16 15:35:22Robin-Nico Kampa, Fabian Deuser, Anna B\"o{\ss}end\"orfer, Konrad Habel, Norbert OswaldAbstract
Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardized benchmark exists to evaluate their ability to design, implement, and train models from scratch across diverse domains. We introduce **1GC-7RC** (*Single Graphic Card: Seven Research Challenges*), a benchmark comprising seven ML tasks spanning language modeling, image classification, semantic segmentation, graph learning, tabular prediction, time-series forecasting, and text classification. Each task provides a locked data-preparation and evaluation script together with a baseline training script; the agent may only modify the training code, has no access to pretrained weights (with one controlled exception for semantic segmentation), no internet access, and must complete each task within a task-specific wall-clock budget (40-120 minutes) on a single GPU. We evaluate seven coding agents: five proprietary (Claude Code with Sonnet 4.6, Opus 4.6, and Opus 4.7; Codex CLI with GPT 5.5; and OpenCode with Qwen 3.6+) and two open-source (OpenCode with Kimi K2.5, Kimi K2.6). Across 5 runs per agent-task pair, we report substantial performance differences that reveal varying levels of implicit ML knowledge, planning ability, and time-budget management. The benchmark, harness, and all evaluation artifacts are publicly available on GitHub at this https URL to facilitate reproducible comparison of future agents. Because our benchmark design is modular, the benchmark can be extended to new tasks and domains, adapted to different GPU budgets, and used to study multi-agent settings, making it a flexible platform for future research on autonomous research agents.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17046
PDF
-
Axial-Relation Guided Fusion State Space Model for Optical-Elevation Sensing Image Segmentation
2026-05-16 02:42:54Feng Gao, Zhilin Jin, Yanhai Gan, Junyu Dong, Qian DuAbstract
Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependencies with linear computational complexity. Moreover, an Axial-Relation Guided Fusion Module is designed to explicitly model global cross-modal correlations along horizontal and vertical axes, enabling efficient feature fusion between optical and elevation modalities. Extensive experiments conducted on the ISPRS Vaihingen and Potsdam datasets demonstrate that our ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency. The code will be made publicly available at \url{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2605.16768
PDF
-
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
2026-05-15 12:51:32Shuaiyi Li, Zhisong Zhang, Yan Wang, Lei Zhu, Dongyang Ma, Chenlong Deng, Yang Deng, Wai LamAbstract
Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained blocks, and the inefficiency of existing block fine-tuning methods that risk degrading performance. To address these, we first construct SemanticSeg, a large and diverse semantic segmentation dataset containing over 30k instances across 16 categories-including books, code, web text, and conversations with text lengths ranging from 2k to 32k. Using this dataset, we train a lightweight segmenter to automatically partition text into human-instinct-aligned blocks with controllable granularity. Second, we propose block distillation, a training framework that is more efficient than block fine-tuning, which uses a frozen full-attention teacher model to guide the block-attention student. This framework integrates three novel components: block sink tokens to mitigate information loss at block boundaries, block dropout to leverage training signals from all blocks, and token-level loss weighting to focus learning on block-attention-sensitive tokens. Experiments across multiple models and benchmarks demonstrate that our segmenter outperforms heuristic and statistical baselines, and block distillation achieves near-full-attention performance under block attention, establishing a practical and scalable pathway for deploying block attention.
Abstract (translated)
URL
https://arxiv.org/abs/2605.15913
PDF
-
Bidirectional Fusion Guided by Cardiac Patterns for Semi-Supervised ECG Segmentation
2026-05-15 08:18:42Jeonghwa Lim, Minje Park, Sunghoon JooAbstract
Accurate delineation of electrocardiogram (ECG), the segmentation of meaningful waveform features, is crucial for cardiovascular diagnostics. However, the scarcity of annotated data poses a significant challenge for training deep learning models. Conventional semi-supervised semantic segmentation (SemiSeg) methods primarily focus on consistency from unlabeled data, underutilizing the information exchange possible between labeled and unlabeled sets. To address this, we introduce CardioMix, a framework built on a bidirectional CutMix strategy guided by cardiac patterns for ECG segmentation. This approach enriches the labeled set with realistic variations from unlabeled data while simultaneously applying stronger supervisory signals to the unlabeled set, as the cardiac pattern-guided mixing ensures all augmented samples remain physiologically meaningful. Our framework is designed as a plug-and-play module, demonstrating high compatibility with various SemiSeg algorithms. Extensive experiments on SemiSegECG, a public multi-dataset benchmark for ECG delineation, demonstrate that CardioMix consistently outperforms existing CutMix-based fusion strategies across diverse datasets and labeled ratios as a plug-and-play module compatible with various SemiSeg algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2605.15722
PDF
