Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Deep Generative Adversarial Hashing Network
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use HashGAN instead of the strongest reported unsupervised hashing baseline | Image retrieval · CIFAR-10, 64 hash bits | mAP (%): 32.53 vs 17.21 | Helped |
| Use HashGAN instead of the strongest reported unsupervised hashing baseline | Image retrieval · MNIST, 64 hash bits | mAP (%): 93.93 vs 46.74 | Helped |
| Use HashGAN instead of the strongest reported unsupervised hashing baseline | Image retrieval · CIFAR-10, 64 hash bits | mAP@1000 (%): 48.12 vs 32.41 | Helped |
| Use HashGAN instead of the strongest reported unsupervised hashing baseline | Image retrieval · MNIST, 64 hash bits | mAP@1000 (%): 96.37 vs 80.23 | Helped |
| Add the adversarial, feature-matching, and synthesized-image ℓ2 losses (ablation) | HashGAN · MNIST and CIFAR-10 | precision@1000 | Helped |
| Add the uniform-frequency hash-bit loss (ablation) | HashGAN · MNIST and CIFAR-10 | precision@1000 | Helped |
| Add the consistency loss for transformed images (ablation) | HashGAN · CIFAR-10 | precision@1000 | Helped |
| Add the consistency loss for transformed images (ablation) | HashGAN · MNIST | precision@1000 | Helped |
| Add the synthesized-image ℓ2-norm loss (ablation) | HashGAN · MNIST and CIFAR-10 | precision@1000 | Helped |
| Add the independent-bit loss (ablation) | HashGAN · MNIST and CIFAR-10 | precision@1000 | Helped |
Closest papers by meaning
- HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN (CVPR 2018 · similarity 0.90)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.89)
- Deep Unsupervised Hashing via External Guidance (ICML 2025 · similarity 0.88)
- Once and for All: Universal Transferable Adversarial Perturbation against Deep Hashing-Based Facial Image Retrieval (AAAI 2024 · similarity 0.86)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · similarity 0.86)
- HUANG: A Robust Diffusion Model-based Targeted Adversarial Attack Against Deep Hashing Retrieval (AAAI 2025 · similarity 0.86)
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.