Research map / Label-efficient and robust learning / Recognition and long-tail
Fast Supervised Discrete Hashing
Jie Gui, Tongliang Liu, Zhenan Sun, Dacheng Tao, Tieniu Tan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| regress labels to hash codes instead of hash codes to labels (FSDH vs SDH) | SDH · CIFAR-10 (128 bits) | training time (s): 406.4 -> 32.8 | Improved |
| regress labels to hash codes (FSDH vs SDH) | SDH · MNIST (64 bits) | training time (s): 128 -> 30.7 | Improved |
| regress labels to hash codes (FSDH vs SDH) | SDH · FRGC faces (32 bits) | training time (s): 2.0 -> 1.2 | Improved |
| regress labels to hash codes (FSDH vs SDH) | SDH · CIFAR-10 (128 bits) | accuracy: 0.649 -> 0.658 | Improved |
| regress labels to hash codes (FSDH vs SDH) | SDH · CIFAR-10 (128 bits) | F-measure at Hamming radius 2: 0.1103 -> 0.1266 | Improved |
| regress labels to hash codes (FSDH vs SDH) | SDH · MNIST (64 bits) | accuracy: 0.963 -> 0.965 | No clear effect |
| regress labels to hash codes (FSDH vs SDH) | SDH · MNIST (64 bits) | F-measure at Hamming radius 2: 0.8419 -> 0.8513 | Improved |
| regress labels to hash codes (FSDH vs SDH) | SDH · FRGC faces (32 bits) | MAP: 0.7775 -> 0.7725 | No clear effect |
| regress labels to hash codes (FSDH vs SDH) | SDH · FRGC faces (32 bits) | accuracy: 0.743 -> 0.753 | Improved |
| use FSDH instead of FastHash | FastHash · MNIST (64 bits) | training time (s): 4661.1 -> 30.7 | Improved |
| use FSDH instead of FastHash | FastHash · MNIST (64 bits) | accuracy: 0.972 -> 0.965 | Hurt |
| use FSDH instead of FastHash | FastHash · CIFAR-10 (128 bits) | training time (s): 1183.3 -> 32.8 | Improved |
Closest papers by meaning
- Deep Supervised Discrete Hashing (NeurIPS 2017 · similarity 0.89)
- Column Sampling Based Discrete Supervised Hashing (AAAI 2016 · similarity 0.89)
- Fast Class-wise Updating for Online Hashing (TPAMI 2020 · similarity 0.88)
- Optimizing affinity-based binary hashing using auxiliary coordinates (NeurIPS 2016 · similarity 0.88)
- MIHash: Online Hashing With Mutual Information (ICCV 2017 · similarity 0.88)
- Towards Optimal Discrete Online Hashing with Balanced Similarity (AAAI 2019 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
