Research map / Architectures and efficiency / RNNs and normalization
Efficient end-to-end learning for quantizable representations
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 |
|---|---|---|---|
| jointly learn quantizable embeddings and sparse hash codes end-to-end | Triplet · Cifar-100 test | Pr@1: 56.78 -> 57.63 | Helped |
| jointly learn quantizable embeddings and sparse hash codes end-to-end | Triplet · Cifar-100 test | SUF: 41.21 -> 97.67 | Helped |
| jointly learn quantizable embeddings and sparse hash codes end-to-end | Npairs · Cifar-100 test | Pr@1: 57.05 -> 58.19 | Helped |
| jointly learn quantizable embeddings and sparse hash codes end-to-end | Npairs · ImageNet val | Pr@1: 15.73 -> 16.95 | Helped |
| jointly learn quantizable embeddings and sparse hash codes end-to-end | Npairs · ImageNet val | SUF: 451.42 -> 478.46 | Helped |
| use end-to-end learned hash codes instead of vector quantization | Triplet · ImageNet val | SUF: 146.26 -> 221.49 | Helped |
| use end-to-end learned hash codes instead of vector quantization | Triplet · ImageNet val | Pr@1: 10.90 -> 11.00 | Helped |
| use end-to-end learned hash codes instead of vector quantization | Triplet · Cifar-100 train | NMI: 76.85 -> 89.11 | Helped |
| use end-to-end learned hash codes instead of vector quantization | Npairs · Cifar-100 test | NMI: 66.69 -> 68.56 | Helped |
| use end-to-end learned hash codes instead of vector quantization | Triplet · ImageNet val | NMI: 45.47 -> 48.52 | Helped |
| set hash sparsity to k=3 rather than k=1 | Npairs-Ours · ImageNet val | SUF: 478.46 -> 53.98 | Hurt |
| set hash sparsity to k=3 rather than k=1 | Npairs-Ours · ImageNet val | Pr@1: 16.95 -> 16.24 | Hurt |
Closest papers by meaning
- End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization (CVPR 2019 · similarity 0.92)
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.90)
- Fast Training of Triplet-Based Deep Binary Embedding Networks (CVPR 2016 · similarity 0.89)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.89)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective (NeurIPS 2021 · 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.