mlsanityData to 7 Oct 2026

Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias

arXiv 2101.07296 ↗First posted 18 Jan 2021cs.CV cs.LGcited by 115

Not on the map. Why?

Abstract (arXiv)

It is widely accepted that reasoning about object shape is important for object recognition. However, the most powerful object recognition methods today do not explicitly make use of object shape during learning. In this work, motivated by recent developments in low-shot learning, findings in developmental psychology, and the increased use of synthetic data in computer vision research, we investigate how reasoning about 3D shape can be used to improve low-shot learning methods' generalization performance. We propose a new way to improve existing low-shot learning approaches by learning a discriminative embedding space using 3D object shape, and using this embedding by learning how to map images into it. Our new approach improves the performance of image-only low-shot learning approaches on multiple datasets. We also introduce Toys4K, a 3D object dataset with the largest number of object categories currently available, which supports low-shot learning.

Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 18 Jan 2021.

Builds on

37 of 61 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  11. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  12. 2016Matching Networks for One Shot Learningcited by 2,246
25 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  2. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  3. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2019A Closer Look at Few-shot Classificationcited by 679
  6. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  11. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  12. 2017Relation Networks for Object Detectioncited by 305
  13. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  14. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  15. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  16. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  17. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  18. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  19. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 190
  20. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  21. 2020PointMixup: Augmentation for Point Cloudscited by 104
  22. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  23. 2017Learning Robust Visual-Semantic Embeddingscited by 56
  24. 2019Baby steps towards few-shot learning with multiple semanticscited by 29
  25. 2020Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognitioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 10; 2024: 8; 2025: 42; 2026: 51.

115 papers.

Sort:

By area:

  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  2. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  3. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  4. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  5. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  6. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  7. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
  8. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  9. 2025AToken: A Unified Tokenizer for Visioncited by 30
  10. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  11. 2024KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Modelscited by 22
  12. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
38 more
  1. 2025FastMesh: Efficient Artistic Mesh Generation via Component Decouplingcited by 17
  2. 2022Time to augment self-supervised visual representation learningcited by 15
  3. 2025Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generationcited by 14
  4. 2025Cube: A Roblox View of 3D Intelligencecited by 14
  5. 2025WorldGrow: Generating Infinite 3D Worldcited by 14
  6. 2023Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognitioncited by 13
  7. 2025Orientation Matters: Making 3D Generative Models Orientation-Alignedcited by 13
  8. 2025Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generationcited by 13
  9. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  10. 2025Assembler: Scalable 3D Part Assembly via Anchor Point Diffusioncited by 11
  11. 2025QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Modelscited by 11
  12. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 11
  13. 2023A Closer Look at Few-Shot 3D Point Cloud Classificationcited by 10
  14. 2024Self-supervised visual learning from interactions with objectscited by 10
  15. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  16. 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentscited by 10
  17. 2025SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modelingcited by 9
  18. 20263D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Imagecited by 9
  19. 2025Auto-Regressive Surface Cuttingcited by 8
  20. 2025Towards Scalable Spatial Intelligence via 2D-to-3D Data Liftingcited by 8
  21. 2025CUPID: Generative 3D Reconstruction via Joint Object and Pose Modelingcited by 8
  22. 2025MeshRipple: Structured Autoregressive Generation of Artist-Meshescited by 8
  23. 2025Are We Ready for RL in Text-to-3D Generation? A Progressive Investigationcited by 8
  24. 2023What Makes for Effective Few-shot Point Cloud Classification?cited by 7
  25. 2023GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learningcited by 7
  26. 2024MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creationcited by 7
  27. 2026MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformercited by 7
  28. 2021Adaptive Feature Interpolation for Low-Shot Image Generationcited by 6
  29. 2022Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalizationcited by 6
  30. 2025Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silkcited by 6
  31. 2026LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flowcited by 6
  32. 2023Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Playcited by 5
  33. 2025Residual Primitive Fitting of 3D Shapes with SuperFrustacited by 5
  34. 2026Nexus: Native Mesh Generation with Diffusioncited by 5
  35. 2023LSFSL: Leveraging Shape Information in Few-shot Learningcited by 4
  36. 2024Odd-One-Out: Anomaly Detection by Comparing with Neighborscited by 4
  37. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  38. 2025Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surfacecited by 4

50 most cited of 115 All 115 (JSON)