Research map / Detection and segmentation / Open-set and few-shot detection
Learning Compact Binary Descriptors With Unsupervised Deep Neural Networks
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 DeepBit instead of D-BRIEF | Local binary descriptors · Brown average across train/test splits | Average 95% ERR: 47.54 -> 40.67 | Helped |
| Use DeepBit instead of D-BRIEF | Local binary descriptors · Brown (Notredame train, Yosemite test) | 95% ERR: 46.22 -> 63.68 | Hurt |
| Use DeepBit instead of DH | Unsupervised hashing · CIFAR-10, 16 bit | mAP (top 1,000): 16.17 -> 19.43 | Helped |
| Use DeepBit instead of DH | Unsupervised hashing · CIFAR-10, 32 bit | mAP (top 1,000): 16.62 -> 24.86 | Helped |
| Use DeepBit instead of DH | Unsupervised hashing · CIFAR-10, 64 bit | mAP (top 1,000): 16.96 -> 27.73 | Helped |
| Use DeepBit instead of SIFT-Internal | Flower categorization features · Oxford 17 Category Flower | categorization accuracy: 70.6 ± 1.6% -> 75.1 ± 2.5% | Helped |
| Use DeepBit instead of SIFT-Internal | Flower categorization feature training · Oxford 17 Category Flower | Training Time (sec): 4 -> 0.07 | Helped |
Closest papers by meaning
- Learning Deep Binary Descriptor With Multi-Quantization (CVPR 2017 · similarity 0.90)
- DLBD: A Self-Supervised Direct-Learned Binary Descriptor (CVPR 2023 · similarity 0.87)
- BinGAN: Learning Compact Binary Descriptors with a Regularized GAN (NeurIPS 2018 · similarity 0.86)
- SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks (CVPR 2019 · similarity 0.85)
- Unsupervised Object Detection with Theoretical Guarantees (NeurIPS 2024 · similarity 0.83)
- Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement (ICML 2024 · similarity 0.82)
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.