Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition (2402.11424v1)

Published 18 Feb 2024 in cs.CV and cs.AI

Abstract: In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end generative GZSL framework called D$3$GZSL. This framework respects seen and synthesized unseen data as in-distribution and out-of-distribution data, respectively, for a more balanced model. D$3$GZSL comprises two core modules: in-distribution dual space distillation (ID$2$SD) and out-of-distribution batch distillation (O$2$DBD). ID$2$SD aligns teacher-student outcomes in embedding and label spaces, enhancing learning coherence. O$2$DBD introduces low-dimensional out-of-distribution representations per batch sample, capturing shared structures between seen and unseen categories. Our approach demonstrates its effectiveness across established GZSL benchmarks, seamlessly integrating into mainstream generative frameworks. Extensive experiments consistently showcase that D$3$GZSL elevates the performance of existing generative GZSL methods, underscoring its potential to refine zero-shot learning practices.The code is available at: https://github.com/PJBQ/D3GZSL.git

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Wasserstein generative adversarial networks. In International conference on machine learning, 214–223. PMLR.
  2. Adaptive confidence smoothing for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11671–11680.
  3. An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, 52–68. Springer.
  4. Cross-layer distillation with semantic calibration. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 7028–7036.
  5. Learning efficient object detection models with knowledge distillation. Advances in neural information processing systems, 30.
  6. A boundary based out-of-distribution classifier for generalized zero-shot learning. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIV 16, 572–588. Springer.
  7. Duet: Cross-modal semantic grounding for contrastive zero-shot learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 405–413.
  8. Multi-modal cycle-consistent generalized zero-shot learning. In Proceedings of the European Conference on Computer Vision (ECCV), 21–37.
  9. Multi-modal ensemble classification for generalized zero shot learning. arXiv preprint arXiv:1901.04623.
  10. Non-generative generalized zero-shot learning via task-correlated disentanglement and controllable samples synthesis. In CVPR.
  11. Graph knows unknowns: Reformulate zero-shot learning as sample-level graph recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 7775–7783.
  12. Contrastive embedding for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2371–2381.
  13. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
  14. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136.
  15. Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606.
  16. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
  17. On the importance of gradients for detecting distributional shifts in the wild. Advances in Neural Information Processing Systems, 34: 677–689.
  18. Class-prototype discriminative network for generalized zero-shot learning. IEEE Signal Processing Letters, 27: 301–305.
  19. Generalized zero-shot learning via over-complete distribution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 13300–13308.
  20. Semantic feature extraction for generalized zero-shot learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 1166–1173.
  21. Semantic autoencoder for zero-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3174–3183.
  22. En-compactness: Self-distillation embedding & contrastive generation for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9306–9315.
  23. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6): 84–90.
  24. Learning to detect unseen object classes by between-class attribute transfer. In 2009 IEEE conference on computer vision and pattern recognition, 951–958. IEEE.
  25. Attribute-based classification for zero-shot visual object categorization. IEEE transactions on pattern analysis and machine intelligence, 36(3): 453–465.
  26. Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint arXiv:1711.09325.
  27. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31.
  28. Leveraging the invariant side of generative zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7402–7411.
  29. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690.
  30. Transfer feature generating networks with semantic classes structure for zero-shot learning. IEEE Access, 7: 176470–176483.
  31. Energy-based out-of-distribution detection. Advances in neural information processing systems, 33: 21464–21475.
  32. Goal-oriented gaze estimation for zero-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 3794–3803.
  33. Out-of-distribution detection for generalized zero-shot action recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9985–9993.
  34. Domain-aware visual bias eliminating for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12664–12673.
  35. A generative model for zero shot learning using conditional variational autoencoders. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2188–2196.
  36. Latent embedding feedback and discriminative features for zero-shot classification. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXII 16, 479–495. Springer.
  37. Automated flower classification over a large number of classes. In 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, 722–729. IEEE.
  38. Zero-shot learning with semantic output codes. Advances in neural information processing systems, 22.
  39. An embarrassingly simple approach to zero-shot learning. In International conference on machine learning, 2152–2161. PMLR.
  40. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550.
  41. 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.
  42. Invertible zero-shot recognition flows. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI 16, 614–631. Springer.
  43. React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems, 34: 144–157.
  44. Out-of-distribution detection with deep nearest neighbors. In International Conference on Machine Learning, 20827–20840. PMLR.
  45. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, 6105–6114. PMLR.
  46. Generalized zero-shot learning via synthesized examples. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4281–4289.
  47. The caltech-ucsd birds-200-2011 dataset.
  48. Multi-label out-of-distribution detection via exploiting sparsity and co-occurrence of labels. Image and Vision Computing, 126: 104548.
  49. A survey of zero-shot learning: Settings, methods, and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2): 1–37.
  50. Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence, 41(9): 2251–2265.
  51. Feature generating networks for zero-shot learning. In CVPR.
  52. 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.
  53. Tackling the generative learning trilemma with denoising diffusion GANs. arXiv preprint arXiv:2112.07804.
  54. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1492–1500.
  55. Robust bidirectional generative network for generalized zero-shot learning. In 2020 IEEE International Conference on Multimedia and Expo (ICME), 1–6. IEEE.
  56. Vgse: Visually-grounded semantic embeddings for zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9316–9325.
  57. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928.
Citations (2)
View on Semantic Scholar

Summary

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

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