Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Quantization Network for Efficient Image Retrieval
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 |
|---|---|---|---|
| DQN vs DNNH | deep hashing · NUS-WIDE | average MAP: +8.0% | Helped |
| DQN vs DNNH | deep hashing · CIFAR-10 | average MAP: 0.581 -> 0.580 | No clear effect |
| add joint PQ loss during training instead of two-step quantization (ablation) | DQN · NUS-WIDE, CIFAR-10, Flickr | average MAP: +1.8%, +2.6%, +3.3% | Helped |
| use OPQ instead of PQ in two-step variant (ablation) | DQN2 · NUS-WIDE, CIFAR-10, Flickr | MAP: 0.766 -> 0.764 | No clear effect |
| use pairwise cosine loss instead of inner-product loss (ablation) | DQN · NUS-WIDE, CIFAR-10, Flickr | average MAP: +9.1%, +4.7%, +13.1% | Helped |
Closest papers by meaning
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.97)
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.93)
- Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval (NeurIPS 2023 · similarity 0.91)
- One Loss for Quantization: Deep Hashing With Discrete Wasserstein Distributional Matching (CVPR 2022 · similarity 0.91)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.89)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · similarity 0.88)
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.