Research map / Architectures and efficiency / RNNs and normalization
End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization
Check 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 |
|---|---|---|---|
| Use hierarchical quantization instead of the quantizable representation baseline | Triplet embedding · Cifar-100 test (test hash table), k_s=1 | Pr@1: 57.63 -> 58.42 | Helped |
| Use hierarchical quantization instead of the quantizable representation baseline | Triplet embedding · ImageNet val, k_s=1 | SUF: 221.49 -> 590.41 | Helped |
| Use hierarchical quantization instead of the quantizable representation baseline | Npairs embedding · ImageNet val, k_s=1 | NMI: 55.09 -> 65.49 | Helped |
| Add label remapping to the hierarchical hash learning method (ablation) | Triplet embedding · Cifar-100 test (test hash table), k_s=1 | Pr@1: 58.16 -> 58.42 | Helped |
| Add label remapping to the hierarchical hash learning method (ablation) | Triplet embedding · Cifar-100 test (test hash table), k_s=2 | Pr@1: 58.18 -> 58.39 | Helped |
| Add label remapping to the hierarchical hash learning method (ablation) | Npairs embedding · Cifar-100 test (test hash table), k_s=1 | Pr@1: 58.04 -> 58.28 | Helped |
| Add label remapping to the hierarchical hash learning method (ablation) | Triplet embedding · Cifar-100 test (test hash table), k_s=2 | SUF: 101.26 -> 98.38 | Hurt |
Closest papers by meaning
- Efficient end-to-end learning for quantizable representations (ICML 2018 · similarity 0.92)
- Deep Quantization Network for Efficient Image Retrieval (AAAI 2016 · similarity 0.88)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.87)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.87)
- Supervised Quantization for Similarity Search (CVPR 2016 · similarity 0.87)
- One Loss for Quantization: Deep Hashing With Discrete Wasserstein Distributional Matching (CVPR 2022 · 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.