mlsanityData to 14 Oct 2026

AffordanceSAM: Segment Anything Once More in Affordance Grounding

arXiv 2504.15650 ↗First posted 22 Apr 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Building a generalized affordance grounding model to identify actionable regions on objects is vital for real-world applications. Existing methods to train the model can be divided into weakly and fully supervised ways. However, the former method requires a complex training framework design and can not infer new actions without an auxiliary prior. While the latter often struggle with limited annotated data and components trained from scratch despite being simpler. This study focuses on fully supervised affordance grounding and overcomes its limitations by proposing AffordanceSAM, which extends SAM's generalization capacity in segmentation to affordance grounding. Specifically, we design an affordance-adaption module and curate a coarse-to-fine annotated dataset called C2F-Aff to thoroughly transfer SAM's robust performance to affordance in a three-stage training manner. Experimental results confirm that AffordanceSAM achieves state-of-the-art (SOTA) performance on the AGD20K benchmark and exhibits strong generalized capacity.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 44 of its 58 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

44 of 58 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023Segment Anythingcited by 8,234
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  8. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  9. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  11. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  12. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
32 more
  1. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  2. 2016Modeling Context in Referring Expressionscited by 1,063
  3. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  4. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  5. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  6. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  7. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  8. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 596
  9. 2018Object Detection with Deep Learning: A Reviewcited by 528
  10. 2023Segment Anything in High Qualitycited by 376
  11. 2023Fast Segment Anythingcited by 290
  12. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  13. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 226
  14. 2016What do different evaluation metrics tell us about saliency models?cited by 185
  15. 2023MotionDirector: Motion Customization of Text-to-Video Diffusion Modelscited by 173
  16. 2018Grounded Human-Object Interaction Hotspots from Videocited by 129
  17. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  18. 2024EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Modelcited by 65
  19. 2023LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Groundingcited by 64
  20. 2024AffordanceLLM: Grounding Affordance from Vision Language Modelscited by 55
  21. 2023HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructionscited by 48
  22. 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
  23. 2023One-Shot Open Affordance Learning with Foundation Modelscited by 45
  24. 2021One-Shot Object Affordance Detection in the Wildcited by 40
  25. 2023Understanding 3D Object Interaction from a Single Imagecited by 33
  26. 2022Affordance Learning from Play for Sample-Efficient Policy Learningcited by 30
  27. 2024GalLoP: Learning Global and Local Prompts for Vision-Language Modelscited by 29
  28. 2020Affordances in Robotic Tasks -- A Surveycited by 28
  29. 2019Learning Grasp Affordance Reasoning through Semantic Relationscited by 23
  30. 2024GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Graspingcited by 15
  31. 2023Visual Affordance Prediction for Guiding Robot Explorationcited by 14
  32. 2023Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspectivecited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025Deforming Videos to Masks: Flow Matching for Referring Video Segmentationcited by 10
  2. 2026AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignmentcited by 5
  3. 2026VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Modelcited by 2
  4. 2026CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objectscited by 1
  5. 2026Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Modelscited by 0
  6. 2026Zero-shot 2D Grounding with Novel Affordance Typescited by 0