Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought

• URL: http://arxiv.org/abs/2605.27764v1
• Date: Tue, 26 May 2026 23:26:52 GMT
• Title: Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought
• Abstract summary: We introduce SegWorld, where the model reasons about the scene through a multi-level visual chain-of-thought.<n>We formalize SegWorld as probabilistic inference, in which proactive observation supplies a linguistic scene context.<n>Experiments show SegWorld matches instruction-driven baselines on target-referential instructions and improves substantially on intent-level ones.
• Score: 61.69802853759301
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply the region to be segmented. However, in real-world embodied interaction, human instructions are often at the intent-level, which includes the desired outcome without naming the region that enables it. To bridge this gap, we introduce SegWorld, where the model reasons about the scene through a multi-level visual chain-of-thought (CoT) before committing to a mask. Before receiving any instructions, it proactively observes the scene, describing visible objects and inferring plausible events they may support. Given an instruction, it continues the chain: from the object relevant to the intent, through the action that satisfies it, to the physical interaction site, the object part that affords the action. We formalize SegWorld as probabilistic inference, in which proactive observation supplies a linguistic scene context that improves mask prediction when instructions are given at the level of intent. We construct an intent-to-part benchmark for evaluating affordance-bearing part segmentation from high-level goals. Experiments show SegWorld matches instruction-driven baselines on target-referential instructions and improves substantially on intent-level ones.

Related papers

• See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding [41.70825455674463]
  SWIM (See What I Mean) is a training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts.<n>We show that SWIM substantially improves text-visual alignment and achieves superior performance over visual-prompt-based methods on fine-grained object understanding benchmarks.
  arXiv  Detail & Related papers  (2026-05-18T08:09:37Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• Unleashing Hierarchical Reasoning: An LLM-Driven Framework for Training-Free Referring Video Object Segmentation [17.238084264485988]
  Referring Video Object (RVOS) aims to segment an object of interest throughout a video based on a language description.<n>bftextPARSE-VOS is a training-free framework powered by Large Language Models (LLMs)<n>bftextPARSE-VOS achieved state-of-the-art performance on three major benchmarks: Ref-YouTube-VOS, Ref-DAVIS17, and MeViS.
  arXiv  Detail & Related papers  (2025-09-06T15:46:23Z)
• Mask Grounding for Referring Image Segmentation [42.69973300692365]
  Referring Image (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Most state-of-the-art (SOTA) methods still suffer from considerable language-image modality gap at the pixel and word level. We introduce a novel Mask Grounding auxiliary task that significantly improves visual grounding within language features.
  arXiv  Detail & Related papers  (2023-12-19T14:34:36Z)
• SAGE: Bridging Semantic and Actionable Parts for GEneralizable Manipulation of Articulated Objects [9.500480417077272]
  We propose a novel framework that bridges semantic and actionable parts of articulated objects to achieve generalizable manipulation under natural language instructions. A part-grounding module maps the semantic parts into so-called Generalizable Actionable Parts (GAParts), which inherently carry information about part motion. An interactive feedback module is incorporated to respond to failures, which closes the loop and increases the robustness of the overall framework.
  arXiv  Detail & Related papers  (2023-12-03T07:22:42Z)
• LISA: Reasoning Segmentation via Large Language Model [68.24075852136761]
  We propose a new segmentation task -- reasoning segmentation. The task is designed to output a segmentation mask given a complex and implicit query text. We present LISA: large Language Instructed Assistant, which inherits the language generation capabilities of multimodal Large Language Models.
  arXiv  Detail & Related papers  (2023-08-01T17:50:17Z)
• Position-Aware Contrastive Alignment for Referring Image Segmentation [65.16214741785633]
  We present a position-aware contrastive alignment network (PCAN) to enhance the alignment of multi-modal features. Our PCAN consists of two modules: 1) Position Aware Module (PAM), which provides position information of all objects related to natural language descriptions, and 2) Contrastive Language Understanding Module (CLUM), which enhances multi-modal alignment.
  arXiv  Detail & Related papers  (2022-12-27T09:13:19Z)
• Locate then Segment: A Strong Pipeline for Referring Image Segmentation [73.19139431806853]
  Referring image segmentation aims to segment the objects referred by a natural language expression. Previous methods usually focus on designing an implicit and recurrent interaction mechanism to fuse the visual-linguistic features to directly generate the final segmentation mask. We present a "Then-Then-Segment" scheme to tackle these problems. Our framework is simple but surprisingly effective.
  arXiv  Detail & Related papers  (2021-03-30T12:25:27Z)
• Are We There Yet? Learning to Localize in Embodied Instruction Following [1.7300690315775575]
  Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem. Key challenges for this task include localizing target locations and navigating to them through visual inputs. We augment the agent's field of view during navigation subgoals with multiple viewing angles, and train the agent to predict its relative spatial relation to the target location at each timestep.
  arXiv  Detail & Related papers  (2021-01-09T21:49:41Z)
• SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor [51.298760338410624]
  We propose a SceneEncoder module to impose a scene-aware guidance to enhance the effect of global information. The module predicts a scene descriptor, which learns to represent the categories of objects existing in the scene. We also design a region similarity loss to propagate distinguishing features to their own neighboring points with the same label.
  arXiv  Detail & Related papers  (2020-01-24T16:53:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.