Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Compositional Prototypical Networks for Few-Shot Classification (2306.06584v1)

Published 11 Jun 2023 in cs.CV

Abstract: It is assumed that pre-training provides the feature extractor with strong class transferability and that high novel class generalization can be achieved by simply reusing the transferable feature extractor. In this work, our motivation is to explicitly learn some fine-grained and transferable meta-knowledge so that feature reusability can be further improved. Concretely, inspired by the fact that humans can use learned concepts or components to help them recognize novel classes, we propose Compositional Prototypical Networks (CPN) to learn a transferable prototype for each human-annotated attribute, which we call a component prototype. We empirically demonstrate that the learned component prototypes have good class transferability and can be reused to construct compositional prototypes for novel classes. Then a learnable weight generator is utilized to adaptively fuse the compositional and visual prototypes. Extensive experiments demonstrate that our method can achieve state-of-the-art results on different datasets and settings. The performance gains are especially remarkable in the 5-way 1-shot setting. The code is available at https://github.com/fikry102/CPN.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Rich Semantics Improve Few-shot Learning. 32nd British Machine Vision Conference.
  2. Andreas, J. 2019. Measuring Compositionality in Representation Learning. In International Conference on Learning Representations.
  3. Learning to learn by gradient descent by gradient descent. In Advances in neural information processing systems, 3981–3989.
  4. Biederman, I. 1987. Recognition-by-components: a theory of human image understanding. Psychological review, 94(2): 115.
  5. Concept Learners for Few-Shot Learning. In International Conference on Learning Representations.
  6. Shaping Visual Representations with Attributes for Few-Shot Recognition. IEEE Signal Processing Letters.
  7. Hsva: Hierarchical semantic-visual adaptation for zero-shot learning. Advances in Neural Information Processing Systems, 34.
  8. A Closer Look at Few-shot Classification. In International Conference on Learning Representations.
  9. Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 9062–9071.
  10. Multi-level semantic feature augmentation for one-shot learning. IEEE Transactions on Image Processing, 28(9): 4594–4605.
  11. A Baseline for Few-Shot Image Classification. In International Conference on Learning Representations.
  12. One-shot learning of object categories. IEEE transactions on pattern analysis and machine intelligence, 28(4): 594–611.
  13. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning, 1126–1135. PMLR. ISBN 2640-3498.
  14. Dropblock: A regularization method for convolutional networks. Advances in neural information processing systems, 31.
  15. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 580–587.
  16. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, 2961–2969.
  17. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
  18. Parts of recognition. Cognition, 18(1-3): 65–96.
  19. Cross Attention Network for Few-shot Classification. Advances in Neural Information Processing Systems, 32: 4003–4014.
  20. Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 7840–7847. ISBN 2374-3468.
  21. Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning. IEEE Transactions on Image Processing.
  22. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25: 1097–1105.
  23. Building machines that learn and think like people. Behavioral and brain sciences, 40.
  24. Adversarial feature hallucination networks for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13470–13479.
  25. Discriminative learning of latent features for zero-shot recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7463–7471.
  26. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3431–3440.
  27. Adaptive poincaré point to set distance for few-shot classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 1926–1934.
  28. Learning from one example through shared densities on transforms. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No. PR00662), volume 1, 464–471. IEEE.
  29. The sun attribute database: Beyond categories for deeper scene understanding. International Journal of Computer Vision, 108(1): 59–81.
  30. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 1532–1543.
  31. Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML. In International Conference on Learning Representations.
  32. Optimization as a model for few-shot learning. In 5th International Conference on Learning Representations, ICLR 2017.
  33. The earth mover’s distance as a metric for image retrieval. International journal of computer vision, 40(2): 99–121.
  34. Meta-Learning with Latent Embedding Optimization. In International Conference on Learning Representations.
  35. Schmidhuber, J. 1987. Evolutionary principles in self-referential learning, or on learning how to learn: the meta-meta-… hook. Ph.D. thesis, Technische Universität München.
  36. Generalized zero-and few-shot learning via aligned variational autoencoders. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8247–8255.
  37. Baby steps towards few-shot learning with multiple semantics. Pattern Recognition Letters, 160: 142–147.
  38. Prototypical Networks for Few-shot Learning. Advances in Neural Information Processing Systems, 30: 4077–4087.
  39. Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1199–1208.
  40. Blockmix: meta regularization and self-calibrated inference for metric-based meta-learning. In Proceedings of the 28th ACM international conference on multimedia, 610–618.
  41. Learning Attention-Guided Pyramidal Features for Few-shot Fine-grained Recognition. Pattern Recognition, 108792.
  42. Rethinking few-shot image classification: a good embedding is all you need? In European Conference on Computer Vision, 266–282. Springer.
  43. Learning compositional representations for few-shot recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 6372–6381.
  44. Visualizing data using t-SNE. Journal of machine learning research, 9(11).
  45. Generalized zero-shot learning via synthesized examples. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4281–4289.
  46. Matching networks for one shot learning. Advances in neural information processing systems, 29: 3630–3638.
  47. The caltech-ucsd birds-200-2011 dataset. Technical Report CNS-TR-2011-001, California Institute of Technology.
  48. The Role of Global Labels in Few-Shot Classification and How to Infer Them. Advances in Neural Information Processing Systems, 34.
  49. f-vaegan-d2: A feature generating framework for any-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10275–10284.
  50. Adaptive cross-modal few-shot learning. Advances in Neural Information Processing Systems, 32: 4847–4857.
  51. Attentional Constellation Nets for Few-Shot Learning. In International Conference on Learning Representations.
  52. SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 1056–1066.
  53. Few-shot learning via embedding adaptation with set-to-set functions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8808–8817.
  54. MetaNODE: Prototype optimization as a neural ODE for few-shot learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 9014–9021.
  55. Prototype Completion with Primitive Knowledge for Few-Shot Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3754–3762.
  56. DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 12203–12213.
  57. Compositional few-shot recognition with primitive discovery and enhancing. In Proceedings of the 28th ACM International Conference on Multimedia, 156–164.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Qiang Lyu (3 papers)
  2. Weiqiang Wang (171 papers)
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - fikry102/CPN (9 stars)