Papers
Topics
Authors
Recent
Search
2000 character limit reached

COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing

Published 26 Feb 2024 in cs.CV | (2402.16424v5)

Abstract: Zero-shot hashing (ZSH) has shown excellent success owing to its efficiency and generalization in large-scale retrieval scenarios. While considerable success has been achieved, there still exist urgent limitations. Existing works ignore the locality relationships of representations and attributes, which have effective transferability between seeable classes and unseeable classes. Also, the continuous-value attributes are not fully harnessed. In response, we conduct a COMprehensive Attribute Exploration for ZSH, named COMAE, which depicts the relationships from seen classes to unseen ones through three meticulously designed explorations, i.e., point-wise, pair-wise and class-wise consistency constraints. By regressing attributes from the proposed attribute prototype network, COMAE learns the local features that are relevant to the visual attributes. Then COMAE utilizes contrastive learning to comprehensively depict the context of attributes, rather than instance-independent optimization. Finally, the class-wise constraint is designed to cohesively learn the hash code, image representation, and visual attributes more effectively. Experimental results on the popular ZSH datasets demonstrate that COMAE outperforms state-of-the-art hashing techniques, especially in scenarios with a larger number of unseen label classes.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. Communications of the ACM 51, 117–122.
  2. Attention-based prototypical learning towards interpretable, confident and robust deep neural networks. arXiv preprint arXiv:1902.06292 .
  3. Hashnet: Deep learning to hash by continuation, in: Proceedings of the IEEE international conference on computer vision, pp. 5608–5617.
  4. Transzero: Attribute-guided transformer for zero-shot learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 330–338.
  5. A simple framework for contrastive learning of visual representations, in: International conference on machine learning, PMLR. pp. 1597–1607.
  6. Contrastive learning from pairwise measurements. Advances in Neural Information Processing Systems 31.
  7. Deep polarized network for supervised learning of accurate binary hashing codes., in: IJCAI, pp. 825–831.
  8. Describing objects by their attributes, in: 2009 IEEE conference on computer vision and pattern recognition, IEEE. pp. 1778–1785.
  9. Hybrid attention-based prototypical networks for noisy few-shot relation classification, in: Proceedings of the AAAI conference on artificial intelligence, pp. 6407–6414.
  10. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE transactions on pattern analysis and machine intelligence 35, 2916–2929.
  11. Sitnet: Discrete similarity transfer network for zero-shot hashing., in: IJCAI, pp. 1767–1773.
  12. Dimensionality reduction by learning an invariant mapping, in: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06), IEEE. pp. 1735–1742.
  13. Contrastive embedding for generalized zero-shot learning, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 2371–2381.
  14. One loss for all: Deep hashing with a single cosine similarity based learning objective. Advances in Neural Information Processing Systems 34, 24286–24298.
  15. A comprehensive survey on deep graph representation learning. arXiv preprint arXiv:2304.05055 .
  16. A survey of data-efficient graph learning. arXiv preprint arXiv:2402.00447 .
  17. Evaluating the performance of resnet model based on image recognition, in: Proceedings of the 2018 International Conference on Computing and Artificial Intelligence, pp. 86–90.
  18. Content-based multimedia information retrieval: State of the art and challenges. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 2, 1–19.
  19. Adaptive prototype learning and allocation for few-shot segmentation, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 8334–8343.
  20. Deep unsupervised image hashing by maximizing bit entropy, in: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2002–2010.
  21. Sphereface: Deep hypersphere embedding for face recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 212–220.
  22. Graph structural-topic neural network, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1065–1073.
  23. Hgk-gnn: Heterogeneous graph kernel based graph neural networks, in: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1129–1138.
  24. Visualizing data using t-sne. Journal of machine learning research 9.
  25. Principal components analysis (pca). Computers & Geosciences 19, 303–342.
  26. Sun attribute database: Discovering, annotating, and recognizing scene attributes, in: 2012 IEEE conference on computer vision and pattern recognition, IEEE. pp. 2751–2758.
  27. A review of generalized zero-shot learning methods. IEEE transactions on pattern analysis and machine intelligence .
  28. Unsupervised hashing with contrastive information bottleneck. arXiv preprint arXiv:2105.06138 .
  29. Supervised discrete hashing, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 37–45.
  30. Hashing on nonlinear manifolds. IEEE Transactions on Image Processing 24, 1839–1851.
  31. Embarrassingly simple binary representation learning, in: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 0–0.
  32. Zero-shot hashing via asymmetric ratio similarity matrix. IEEE Transactions on Knowledge and Data Engineering 35, 5426–5437.
  33. Deep convolutional neural network based medical concept normalization. IEEE Transactions on Big Data 8, 1195–1208.
  34. Unsupervised hashing with contrastive learning by exploiting similarity knowledge and hidden structure of data, in: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6350–6358.
  35. Greedy hash: Towards fast optimization for accurate hash coding in cnn. Advances in neural information processing systems 31.
  36. Locality and compositionality in zero-shot learning. arXiv preprint arXiv:1912.12179 .
  37. Fedproto: Federated prototype learning across heterogeneous clients, in: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8432–8440.
  38. Robust image hashing, in: Proceedings 2000 International Conference on Image Processing (Cat. No. 00CH37101), IEEE. pp. 664–666.
  39. The caltech-ucsd birds-200-2011 dataset .
  40. Additive margin softmax for face verification. IEEE Signal Processing Letters 25, 926–930.
  41. Deep supervised hashing with triplet labels, in: Computer Vision–ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I 13, Springer. pp. 70–84.
  42. Spectral hashing. Advances in neural information processing systems 21.
  43. Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence 41, 2251–2265.
  44. Attribute prototype network for zero-shot learning. Advances in Neural Information Processing Systems 33, 21969–21980.
  45. Attribute hashing for zero-shot image retrieval, in: 2017 IEEE International Conference on Multimedia and Expo (ICME), IEEE. pp. 133–138.
  46. Zero-shot hashing via transferring supervised knowledge, in: Proceedings of the 24th ACM international conference on Multimedia, pp. 1286–1295.
  47. Weighted contrative hashing, in: Proceedings of the Asian Conference on Computer Vision, pp. 3861–3876.
  48. Central similarity quantization for efficient image and video retrieval, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 3083–3092.
  49. Zero-shot hashing with orthogonal projection for image retrieval. Pattern Recognition Letters 117, 201–209.
  50. Learning multi-attention convolutional neural network for fine-grained image recognition, in: Proceedings of the IEEE international conference on computer vision, pp. 5209–5217.
  51. Semantic-guided zero-shot learning for low-light image/video enhancement, in: Proceedings of the IEEE/CVF Winter conference on applications of computer vision, pp. 581–590.
  52. Angular deep supervised hashing for image retrieval. IEEE Access 7, 127521–127532.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up