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

High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning (2404.04953v1)

Published 7 Apr 2024 in cs.CV

Abstract: Zero-shot learning(ZSL) aims to recognize new classes without prior exposure to their samples, relying on semantic knowledge from observed classes. However, current attention-based models may overlook the transferability of visual features and the distinctiveness of attribute localization when learning regional features in images. Additionally, they often overlook shared attributes among different objects. Highly discriminative attribute features are crucial for identifying and distinguishing unseen classes. To address these issues, we propose an innovative approach called High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning (HDAFL). HDAFL optimizes visual features by learning attribute features to obtain discriminative visual embeddings. Specifically, HDAFL utilizes multiple convolutional kernels to automatically learn discriminative regions highly correlated with attributes in images, eliminating irrelevant interference in image features. Furthermore, we introduce a Transformer-based attribute discrimination encoder to enhance the discriminative capability among attributes. Simultaneously, the method employs contrastive loss to alleviate dataset biases and enhance the transferability of visual features, facilitating better semantic transfer between seen and unseen classes. Experimental results demonstrate the effectiveness of HDAFL across three widely used datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Label-embedding for image classification. IEEE transactions on pattern analysis and machine intelligence 38, 7 (2015), 1425–1438.
  2. Léon Bottou. 2010. Large-scale machine learning with stochastic gradient descent. In Proceedings of COMPSTAT’2010: 19th International Conference on Computational StatisticsParis France, August 22-27, 2010 Keynote, Invited and Contributed Papers. Springer, 177–186.
  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. Springer, 52–68.
  4. Transzero: Attribute-guided transformer for zero-shot learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 330–338.
  5. Msdn: Mutually semantic distillation network for zero-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 7612–7621.
  6. Free: Feature refinement for generalized zero-shot learning. In Proceedings of the IEEE/CVF international conference on computer vision. 122–131.
  7. Hsva: Hierarchical semantic-visual adaptation for zero-shot learning. Advances in Neural Information Processing Systems 34 (2021), 16622–16634.
  8. Zero-Shot Learning by Harnessing Adversarial Samples. In Proceedings of the 31st ACM International Conference on Multimedia. 4138–4146.
  9. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248–255.
  10. Transductive multi-view zero-shot learning. IEEE transactions on pattern analysis and machine intelligence 37, 11 (2015), 2332–2345.
  11. Contrastive embedding for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2371–2381.
  12. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
  13. Dat Huynh and Ehsan Elhamifar. 2020. Fine-grained generalized zero-shot learning via dense attribute-based attention. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4483–4493.
  14. Transferable contrastive network for generalized zero-shot learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9765–9774.
  15. Generalized zero-shot learning via over-complete distribution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 13300–13308.
  16. Supervised contrastive learning. Advances in Neural Information Processing Systems 33 (2020), 18661–18673.
  17. 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.
  18. Learning to detect unseen object classes by between-class attribute transfer. 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009), 951–958. https://api.semanticscholar.org/CorpusID:10301835
  19. Attribute-based classification for zero-shot visual object categorization. IEEE transactions on pattern analysis and machine intelligence 36, 3 (2013), 453–465.
  20. Leveraging the invariant side of generative zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7402–7411.
  21. Discriminative learning of latent features for zero-shot recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7463–7471.
  22. Generalized zero-shot learning with deep calibration network. Advances in neural information processing systems 31 (2018).
  23. Goal-oriented gaze estimation for zero-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3794–3803.
  24. Task aligned generative meta-learning for zero-shot learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 8723–8731.
  25. Latent embedding feedback and discriminative features for zero-shot classification. In European Conference on Computer Vision. Springer, 479–495.
  26. Genevieve Patterson and James Hays. 2012. Sun attribute database: Discovering, annotating, and recognizing scene attributes. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2751–2758.
  27. Contrastive learning with hard negative samples. arXiv preprint arXiv:2010.04592 (2020).
  28. 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.
  29. Invertible zero-shot recognition flows. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI 16. Springer, 614–631.
  30. Transductive unbiased embedding for zero-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1024–1033.
  31. Distinguishing unseen from seen for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7885–7894.
  32. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).
  33. Generalized zero-shot learning via synthesized examples. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4281–4289.
  34. Leveraging seen and unseen semantic relationships for generative zero-shot learning. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXX 16. Springer, 70–86.
  35. Task-independent knowledge makes for transferable representations for generalized zero-shot learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 2710–2718.
  36. Zero-shot learning via class-conditioned deep generative models. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32.
  37. Caltech-UCSD birds 200. (2010).
  38. Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence 41, 9 (2018), 2251–2265.
  39. Feature generating networks for zero-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5542–5551.
  40. 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.
  41. Attentive region embedding network for zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9384–9393.
  42. Region graph embedding network for zero-shot learning. In European conference on computer vision. Springer, 562–580.
  43. Attribute prototype network for zero-shot learning. Advances in Neural Information Processing Systems 33 (2020), 21969–21980.
  44. Episode-based prototype generating network for zero-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 14035–14044.
  45. A generative adversarial approach for zero-shot learning from noisy texts. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1004–1013.
  46. Semantic-guided multi-attention localization for zero-shot learning. Advances in Neural Information Processing Systems 32 (2019).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Yu Lei (57 papers)
  2. Guoshuai Sheng (1 paper)
  3. Fangfang Li (16 papers)
  4. Quanxue Gao (14 papers)
  5. Cheng Deng (67 papers)
  6. Qin Li (179 papers)
Citations (1)
View on Semantic Scholar

Summary

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

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