Research map / Label-efficient and robust learning / Self-supervised and contrastive
Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing
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 self-supervised structure-sensitive learning | Attention · LIP validation | Mean IoU: 42.92 -> 44.73 | Helped |
| Add self-supervised structure-sensitive learning | DeepLabV2 · LIP validation | Mean IoU: 41.64 -> 42.44 | Helped |
| Add self-supervised structure-sensitive learning | Attention · LIP test | Mean IoU: 42.97 -> 44.59 | Helped |
| Add self-supervised structure-sensitive learning | DeepLabV2 · LIP test | Mean IoU: 41.56 -> 42.46 | Helped |
| Add self-supervised structure-sensitive learning | Attention · PASCAL-Person-Part | Avg IoU: 56.39 -> 59.36 | Helped |
| Add self-supervised structure-sensitive learning | Attention · ATR | Mean IoU: 49.35 -> 52.69 | Helped |
| Add self-supervised structure-sensitive learning | DeepLabV2 · ATR | Mean IoU: 48.64 -> 49.92 | Helped |
| Add self-supervised structure-sensitive learning | DeepLabV2 · LIP | Mean IoU: 43.97 -> 44.81 | Helped |
| Add self-supervised structure-sensitive learning | Attention · LIP | Mean IoU: 45.38 -> 46.85 | Helped |
| Add self-supervised structure-sensitive learning | DeepLabV2 · LIP validation, small objects | Mean IoU: 28.77 -> 30.05 | Hurt |
Closest papers by meaning
- Pose-Guided Human Parsing by an AND/OR Graph Using Pose-Context Features (AAAI 2016 · similarity 0.91)
- Devil in the Details: Towards Accurate Single and Multiple Human Parsing (AAAI 2019 · similarity 0.91)
- Part-Aware Context Network for Human Parsing (CVPR 2020 · similarity 0.89)
- CDGNet: Class Distribution Guided Network for Human Parsing (CVPR 2022 · similarity 0.89)
- PLIP: Language-Image Pre-training for Person Representation Learning (NeurIPS 2024 · similarity 0.85)
- DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval (AAAI 2025 · similarity 0.85)
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.