mlsanityData to 7 Oct 2026

One-Shot Transfer of Affordance Regions? AffCorrs!

arXiv 2209.07147 ↗First posted 15 Sep 2022cs.CV cs.ROcited by 31

Not on the map. Why?

Abstract (arXiv)

In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance regions, we segment semantically corresponding parts within a target scene. We propose AffCorrs, an unsupervised model that combines the properties of pre-trained DINO-ViT's image descriptors and cyclic correspondences. We use AffCorrs to find corresponding affordances both for intra- and inter-class one-shot part segmentation. This task is more difficult than supervised alternatives, but enables future work such as learning affordances via imitation and assisted teleoperation.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

27 of 42 references.

References · 27

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2017One-Shot Learning for Semantic Segmentationcited by 337
  4. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  5. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  6. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  7. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  8. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  9. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  10. 2017AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detectioncited by 126
  11. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  12. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
15 more
  1. 2022NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fieldscited by 86
  2. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  3. 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulationcited by 49
  4. 2018One-Shot Instance Segmentationcited by 43
  5. 2021Warp Consistency for Unsupervised Learning of Dense Correspondencescited by 42
  6. 2021One-Shot Affordance Detectioncited by 32
  7. 2022Affordance Learning from Play for Sample-Efficient Policy Learningcited by 27
  8. 2017Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networkscited by 21
  9. 2021Learning 3D Dense Correspondence via Canonical Point Autoencodercited by 21
  10. 2021Unsupervised Co-part Segmentation through Assemblycited by 12
  11. 2021Learning Contrastive Representation for Semantic Correspondencecited by 11
  12. 2019Learning Semantic Correspondence Exploiting an Object-level Priorcited by 5
  13. 2021Fully Self-Supervised Class Awareness in Dense Object Descriptorscited by 5
  14. 2016Towards Lifelong Self-Supervision: A Deep Learning Direction for Roboticscited by 3
  15. 2020Visual Descriptor Learning from Monocular Videocited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 12; 2025: 8; 2026: 3.

31 papers.

Sort:

By area:

  1. 2023LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Groundingcited by 64
  2. 2024AffordanceLLM: Grounding Affordance from Vision Language Modelscited by 55
  3. 2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 51
  4. 2024DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Modelscited by 43
  5. 2023Open-Vocabulary Affordance Detection in 3D Point Cloudscited by 41
  6. 2023Dexterous Functional Graspingcited by 36
  7. 2023SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networkscited by 24
  8. 2023One-Shot Imitation Learning: A Pose Estimation Perspectivecited by 21
  9. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 17
  10. 2024Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Taskscited by 16
  11. 2024WorldAfford: Affordance Grounding based on Natural Language Instructionscited by 14
  12. 2025GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulationcited by 14
19 more
  1. 2024INTRA: Interaction Relationship-aware Weakly Supervised Affordance Groundingcited by 12
  2. 2024Seeing the Unseen: Visual Common Sense for Semantic Placementcited by 9
  3. 20252HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videoscited by 9
  4. 2025Mobi-π: Mobilizing Your Robot Learning Policycited by 9
  5. 2025Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priorscited by 9
  6. 2023NOIR: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 8
  7. 2025Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scalecited by 6
  8. 2023Text-Guided Vector Graphics Customizationcited by 5
  9. 2026AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignmentcited by 5
  10. 2024Self-Explainable Affordance Learning with Embodied Captioncited by 4
  11. 2024Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splattingcited by 4
  12. 2025Watch Your STEPP: Semantic Traversability Estimation using Pose Projected Featurescited by 4
  13. 2024Visual Imitation Learning of Task-Oriented Object Grasping and Rearrangementcited by 3
  14. 2025Visual Affordance Prediction: Survey and Reproducibilitycited by 1
  15. 2023AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViTcited by 0
  16. 2024Adapting Skills to Novel Grasps: A Self-Supervised Approachcited by 0
  17. 2025TReF-6: Inferring Task-Relevant Frames from a Single Demonstration for One-Shot Skill Generalizationcited by 0
  18. 2026RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignmentcited by 0
  19. 2026Zero-shot 2D Grounding with Novel Affordance Typescited by 0