Abstract | ||
---|---|---|
Label Distribution Learning (LDL) can better describe the real-world data by learning a set of label distributions instead of discrete binary labels. Particularly, hashing-based LDL has achieved promising performance due to its desirable advantages of fast similarity computation and extremely low storage cost. However, existing hashing-based LDL methods are still shallow learning methods, which cannot deeply capture the implicit data semantics, and meanwhile fail to fully model the semantic data relations. In this letter, we propose an effective and efficient Deep Discrete Hashing for Label Distribution Learning (DDH-LDL) method, which develops the first deep hashing framework for LDL. Specifically, DDH-LDL captures implicit semantic information by multi-layer non-linear transformation, and simultaneously preserves the modeled semantic relations of instances into hash codes via semantic message aggregation on Graph Convolutional Network (GCN). Furthermore, we elaborately design a discrete optimization module that is seamlessly integrated into our proposed deep hashing framework to reduce the binary quantization errors. Experiments on several widely tested datasets verify the superiority of the proposed method on both learning accuracy and efficiency. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/LSP.2022.3158229 | IEEE SIGNAL PROCESSING LETTERS |
Keywords | DocType | Volume |
Codes, Semantics, Optimization, Hash functions, Encoding, Data models, Training, Label distribution learning, deep hashing, discrete optimization | Journal | 29 |
ISSN | Citations | PageRank |
1070-9908 | 0 | 0.34 |
References | Authors | |
17 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhen Zhang | 1 | 4 | 12.55 |
Lei Zhu | 2 | 854 | 51.69 |
Yaping Li | 3 | 0 | 0.34 |
Yang Xu | 4 | 41 | 5.60 |