Research map / Image generation / Autoregressive and latent generation
HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN
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 |
|---|---|---|---|
| Add PC-WGAN-generated images for hash encoder training (ablation) | HashGAN · NUS-WIDE, CIFAR-10, and MS-COCO | average MAP: 2.5%, 3.8% and 1.8% | Helped |
| Use cosine cross-entropy instead of inner-product cross-entropy (ablation) | HashGAN · NUS-WIDE, CIFAR-10, and MS-COCO | average MAP: 2.0%, 2.5% and 1.9% | Helped |
| Add cosine quantization loss (ablation) | HashGAN · NUS-WIDE, CIFAR-10, and MS-COCO | average MAP: 4.7%, 3.8%, and 5.3% | Helped |
| Add binarization of continuous hash representations (ablation) | HashGAN · NUS-WIDE, CIFAR-10, and MS-COCO | average MAP: 3.0%, 2.0%, and 2.6% | Hurt |
| Use HashGAN rather than HashNet | deep hashing · NUS-WIDE, 64 bits | MAP@5000: 0.716 -> 0.748 | Helped |
| Use HashGAN rather than HashNet | deep hashing · CIFAR-10, 64 bits | MAP@54000: 0.687 -> 0.749 | Helped |
| Use HashGAN rather than HashNet | deep hashing · MS-COCO, 64 bits | MAP@5000: 0.736 -> 0.744 | Helped |
Closest papers by meaning
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.92)
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.92)
- Deep Quantization Network for Efficient Image Retrieval (AAAI 2016 · similarity 0.91)
- Unsupervised Deep Generative Adversarial Hashing Network (CVPR 2018 · similarity 0.90)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · 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.