Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Deep Feature Representations With Domain Guided Dropout for Person Re-Identification
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 |
|---|---|---|---|
| Add deterministic Domain Guided Dropout after joint training (ablation) | JSTL · CUHK03 | CMC top-1 accuracy: 72.0 -> 72.5 | Helped |
| Add deterministic Domain Guided Dropout after joint training (ablation) | JSTL · CUHK01 | CMC top-1 accuracy: 62.1 -> 63.0 | Helped |
| Add deterministic Domain Guided Dropout after joint training (ablation) | JSTL · PRID | CMC top-1 accuracy: 59.0 -> 60.0 | Helped |
| Add deterministic Domain Guided Dropout after joint training (ablation) | JSTL · VIPeR | CMC top-1 accuracy: 35.4 -> 37.7 | Helped |
| Add deterministic Domain Guided Dropout after joint training (ablation) | JSTL · 3DPeS | CMC top-1 accuracy: 44.5 -> 45.6 | Helped |
| Add deterministic Domain Guided Dropout after joint training (ablation) | JSTL · iLIDS | CMC top-1 accuracy: 56.9 -> 59.6 | Helped |
| Add stochastic Domain Guided Dropout during domain-specific fine-tuning (ablation) | JSTL+DGD · CUHK03 | CMC top-1 accuracy: 74.8 -> 75.3 | Helped |
| Add stochastic Domain Guided Dropout during domain-specific fine-tuning (ablation) | JSTL+DGD · CUHK01 | CMC top-1 accuracy: 66.2 -> 66.6 | Helped |
| Add stochastic Domain Guided Dropout during domain-specific fine-tuning (ablation) | JSTL+DGD · PRID | CMC top-1 accuracy: 57.0 -> 64.0 | Helped |
| Add stochastic Domain Guided Dropout during domain-specific fine-tuning (ablation) | JSTL+DGD · VIPeR | CMC top-1 accuracy: 37.7 -> 38.6 | Helped |
| Add stochastic Domain Guided Dropout during domain-specific fine-tuning (ablation) | JSTL+DGD · 3DPeS | CMC top-1 accuracy: 54.0 -> 56.0 | Helped |
| Add stochastic Domain Guided Dropout during domain-specific fine-tuning (ablation) | JSTL+DGD · iLIDS | CMC top-1 accuracy: 61.1 -> 64.6 | Helped |
Closest papers by meaning
- Deep Neural Networks with Inexact Matching for Person Re-Identification (NeurIPS 2016 · similarity 0.88)
- Resource Aware Person Re-Identification Across Multiple Resolutions (CVPR 2018 · similarity 0.88)
- Backbone Cannot Be Trained at Once: Rolling Back to Pre-Trained Network for Person Re-Identification (AAAI 2019 · similarity 0.87)
- Generalizable Person Re-Identification by Domain-Invariant Mapping Network (CVPR 2019 · similarity 0.87)
- Domain Adaptive Attention Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.87)
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification (CVPR 2021 · similarity 0.87)
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.