Research map / Label-efficient and robust learning / Knowledge distillation
Robust Re-Identification by Multiple Views Knowledge Distillation
Angelo Porrello, Luca Bergamini, Simone Calderara
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| distil across viewpoints instead of time only (ablation) | ResTKD-50 student · MARS | viewpoint classification accuracy (lower = less camera bias): 0.69 -> 0.49 | Improved |
| distil across viewpoints instead of time only (ablation) | ResTKD-50 student · Duke-Video-ReID | viewpoint classification accuracy (lower = less camera bias): 0.76 -> 0.69 | Improved |
| time-based distillation versus the teacher (ablation) | ResTKD-50 student · MARS | viewpoint classification accuracy: 0.74 -> 0.69 | No clear effect |
Closest papers by meaning
- Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification (AAAI 2020 · similarity 0.82)
- Distilled Person Re-Identification: Towards a More Scalable System (CVPR 2019 · similarity 0.82)
- Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification (ECCV 2020 · similarity 0.82)
- Learning Robust Event-Guided Representations for Person Re-Identification (IJCV 2026 · similarity 0.81)
- Progressive Multi-modal Knowledge Distillation for Multi-spectral Object Re-identification (AAAI 2026 · similarity 0.80)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · similarity 0.79)
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.
