Research map / Learning theory and algorithms / Prediction and decision losses
Hashing as Tie-Aware Learning to Rank
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 |
|---|---|---|---|
| optimize tie-aware AP directly with TALR-AP | VGG-F hashing · CIFAR-10 S1, 48 bits | AP_T: 0.822 -> 0.826 | Helped |
| optimize tie-aware AP directly with TALR-AP | VGG-F hashing · NUS-WIDE S1, 48 bits | AP_T: 0.723 -> 0.752 | Helped |
| optimize tie-aware AP directly with TALR-AP | VGG-F hashing · CIFAR-10 S2, 48 bits | AP_T: 0.942 -> 0.945 | Helped |
| optimize tie-aware AP directly with TALR-AP | VGG-F hashing · NUS-WIDE S2, 48 bits | AP@5K: 0.838 -> 0.862 | Helped |
| optimize tie-aware AP directly with TALR-AP | AlexNet hashing · ImageNet100, 64 bits | AP@1000: 0.6947 -> 0.7053 | Helped |
| optimize tie-aware NDCG directly with TALR-NDCG | VGG-F hashing · NUS-WIDE, 64 bits | NDCG: 0.913 -> 0.927 | Helped |
| optimize tie-aware NDCG directly with TALR-NDCG | linear hash on GIST features · LabelMe, 64 bits | NDCG: 0.915 -> 0.917 | Helped |
| increase tanh scaling alpha over time instead of keeping alpha fixed at 40 (ablation) | TALR-AP · CIFAR-10 S1, 12 bits | AP_T: 0.732 -> 0.751 | Helped |
| increase tanh scaling alpha over time instead of keeping alpha fixed at 40 (ablation) | TALR-AP · CIFAR-10 S1, 48 bits | AP_T: 0.826 -> 0.830 | Helped |
Closest papers by meaning
- Discretely Coding Semantic Rank Orders for Supervised Image Hashing (CVPR 2017 · similarity 0.90)
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.89)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.89)
- Deep Quantization Network for Efficient Image Retrieval (AAAI 2016 · similarity 0.88)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.87)
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · 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.