Research map / Learning theory and algorithms / Prediction and decision losses
A Lower Bound of Hash Codes' Performance
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 |
|---|---|---|---|
| Integrate the proposed objective and posterior estimation into existing hash models | HashNet, DBDH, DSDH, DCH, GreedHash, and CSQ · CIFAR-10, NUS-WIDE, and ImageNet | mAP@R: up to 26.5% increase | Helped |
| Integrate the proposed method into CSQ | CSQ · CIFAR-10, 16 bits | mAP@R: 83.2 -> 88.7 | Helped |
| Integrate the proposed method into CSQ | CSQ · CIFAR-10, 32 bits | mAP@R: 83.4 -> 89.2 | Helped |
| Integrate the proposed method into CSQ | CSQ · CIFAR-10, 64 bits | mAP@R: 84.7 -> 90.3 | Helped |
| Integrate the proposed method into CSQ | CSQ · NUS-WIDE, 16 bits | mAP@R: 82.0 -> 83.3 | Helped |
| Integrate the proposed method into CSQ | CSQ · NUS-WIDE, 32 bits | mAP@R: 83.5 -> 85.3 | Helped |
| Integrate the proposed method into CSQ | CSQ · NUS-WIDE, 64 bits | mAP@R: 84.6 -> 85.8 | Helped |
| Integrate the proposed method into CSQ | CSQ · ImageNet, 16 bits | mAP@R: 83.4 -> 88.5 | Helped |
| Integrate the proposed method into CSQ | CSQ · ImageNet, 32 bits | mAP@R: 86.9 -> 89.5 | Helped |
| Integrate the proposed method into CSQ | CSQ · ImageNet, 64 bits | mAP@R: 87.9 -> 90.2 | Helped |
| Integrate the proposed method into hash models | HashNet, DBDH, DSDH, DCH, GreedHash, and CSQ · ImageNet | accuracy: up to 20.5% increase | Helped |
| Replace the proposed posterior estimator with BCE loss (ablation) | CSQ_D · ImageNet | mAP@R | Hurt |
Closest papers by meaning
- One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective (NeurIPS 2021 · similarity 0.88)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.86)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.86)
- KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing (AAAI 2025 · similarity 0.85)
- An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing (CVPR 2024 · similarity 0.85)
- Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery (NeurIPS 2024 · similarity 0.85)
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.