mlsanityData to 14 Oct 2026

One-Shot Object Affordance Detection in the Wild

arXiv 2108.03658 ↗First posted 8 Aug 2021cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Affordance detection refers to identifying the potential action possibilities of objects in an image, which is a crucial ability for robot perception and manipulation. To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i.e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected. To this end, we devise a One-Shot Affordance Detection Network (OSAD-Net) that firstly estimates the human action purpose and then transfers it to help detect the common affordance from all candidate images. Through collaboration learning, OSAD-Net can capture the common characteristics between objects having the same underlying affordance and learn a good adaptation capability for perceiving unseen affordances. Besides, we build a large-scale Purpose-driven Affordance Dataset v2 (PADv2) by collecting and labeling 30k images from 39 affordance and 103 object categories. With complex scenes and rich annotations, our PADv2 dataset can be used as a test bed to benchmark affordance detection methods and may also facilitate downstream vision tasks, such as scene understanding, action recognition, and robot manipulation. Specifically, we conducted comprehensive experiments on PADv2 dataset by including 11 advanced models from several related research fields. Experimental results demonstrate the superiority of our model over previous representative ones in terms of both objective metrics and visual quality. The benchmark suite is available at https://github.com/lhc1224/OSAD Net.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 63 of its 119 references that are in the map. First posted on arXiv 8 Aug 2021.

Builds on

63 of 119 references.

References · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  9. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  12. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
38 more
  1. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  2. 2016Pyramid Scene Parsing Networkcited by 2,479
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  6. 2016Generative Adversarial Imitation Learningcited by 1,597
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  9. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  13. 2017One-Shot Learning for Semantic Segmentationcited by 337
  14. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  15. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 260
  16. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  17. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  18. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  19. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  20. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  21. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  22. 2018Grounded Human-Object Interaction Hotspots from Videocited by 129
  23. 2017AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detectioncited by 128
  24. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 123
  25. 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 111
  26. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  27. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  28. 2020Highly Efficient Salient Object Detection with 100K Parameterscited by 79
  29. 2017Learning to Act Properly: Predicting and Explaining Affordances from Imagescited by 74
  30. 2019Putting Humans in a Scene: Learning Affordance in 3D Indoor Environmentscited by 72
  31. 2020Learning Affordance Landscapes for Interaction Exploration in 3D Environmentscited by 65
  32. 2020An Exploration of Embodied Visual Explorationcited by 58
  33. 2020Re-thinking Co-Salient Object Detectioncited by 54
  34. 2018Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervisioncited by 52
  35. 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
  36. 2018Binge Watching: Scaling Affordance Learning from Sitcomscited by 41
  37. 2021One-Shot Affordance Detectioncited by 32
  38. 2018Interact as You Intend: Intention-Driven Human-Object Interaction Detectioncited by 30

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 11; 2024: 11; 2025: 11; 2026: 2.

40 papers.

Sort:

By area:

  1. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  2. 2023Grounding 3D Object Affordance from 2D Interactions in Imagescited by 62
  3. 2025Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spacescited by 54
  4. 2023LEMON: Learning 3D Human-Object Interaction Relation from 2D Imagescited by 49
  5. 2023Open-Vocabulary Affordance Detection in 3D Point Cloudscited by 41
  6. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  7. 2023Affordance Grounding from Demonstration Video to Target Imagecited by 34
  8. 2024GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Groundingcited by 28
  9. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  10. 2022Grounded Affordance from Exocentric Viewcited by 22
  11. 2023Deep Graph Reprogrammingcited by 22
  12. 2022Phrase-Based Affordance Detection via Cyclic Bilateral Interactioncited by 19
28 more
  1. 2023Multi-label affordance mapping from egocentric visioncited by 18
  2. 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentationcited by 17
  3. 2024Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intentioncited by 16
  4. 2022Discovering Human-Object Interaction Concepts via Self-Compositional Learningcited by 15
  5. 2023RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environmentscited by 15
  6. 2024WorldAfford: Affordance Grounding based on Natural Language Instructionscited by 14
  7. 2024Grounding 3D Scene Affordance From Egocentric Interactionscited by 11
  8. 2024PEAR: Phrase-Based Hand-Object Interaction Anticipationcited by 10
  9. 2024Text-driven Affordance Learning from Egocentric Visioncited by 9
  10. 20252HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videoscited by 9
  11. 2024Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentionscited by 8
  12. 2024MambaPupil: Bidirectional Selective Recurrent model for Event-based Eye trackingcited by 8
  13. 2023Spatial-Aware Token for Weakly Supervised Object Localizationcited by 7
  14. 2023Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmarkcited by 7
  15. 2025AffordanceSAM: Segment Anything Once More in Affordance Groundingcited by 6
  16. 2025One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenescited by 3
  17. 2025Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulationcited by 3
  18. 2025Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Groundingcited by 3
  19. 2025O3Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulationcited by 3
  20. 2024Visual-Geometric Collaborative Guidance for Affordance Learningcited by 2
  21. 2025Unlocking 3D Affordance Segmentation with 2D Semantic Knowledgecited by 2
  22. 2025Visual Affordance Prediction: Survey and Reproducibilitycited by 1
  23. 2025Object Affordance Recognition and Grounding via Multi-scale Cross-modal Representation Learningcited by 1
  24. 2026Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spacescited by 1
  25. 2023Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learningcited by 0
  26. 2024Leverage Task Context for Object Affordance Rankingcited by 0
  27. 2025YOLOA: Real-Time Affordance Detection via LLM Adaptercited by 0
  28. 2026Zero-shot 2D Grounding with Novel Affordance Typescited by 0