Research map / Detection and segmentation / Open-set and few-shot detection
Objects as Context for Detecting Their Semantic Parts
Read the paperCheck 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 object appearance (ablation) | AlexNet part-appearance baseline · PASCAL-Part val | mAP: 22.1 -> 25.1 | Helped |
| add object class (ablation) | AlexNet part-appearance baseline · PASCAL-Part val | mAP: 22.1 -> 23.0 | Helped |
| add object appearance and class rather than appearance alone (ablation) | AlexNet part detector · PASCAL-Part val | mAP: 25.1 -> 25.7 | Helped |
| add relative-location OffsetNet with one mode per class (ablation) | AlexNet part-appearance baseline · PASCAL-Part val | mAP: 22.1 -> 24.3 | Helped |
| use prior-based variable number of OffsetNet modes instead of one mode (ablation) | AlexNet part detector with OffsetNet · PASCAL-Part val | mAP: 24.3 -> 24.7 | Helped |
| combine object appearance and relative location (ablation) | AlexNet part detector · PASCAL-Part val | mAP: 25.1 -> 26.8 | Helped |
| combine object appearance, object class, and relative location (ablation) | AlexNet part detector · PASCAL-Part val | mAP: 22.1 -> 27.4 | Helped |
| add bounding-box regression (ablation) | AlexNet part-appearance baseline · PASCAL-Part val | mAP: 22.1 -> 24.5 | Helped |
| combine object appearance, object class, and relative location with bounding-box regression (ablation) | AlexNet part detector · PASCAL-Part val | mAP: 24.5 -> 29.5 | Helped |
| add object appearance to VGG16 part detector (ablation) | VGG16 part-appearance baseline with bounding-box regression · PASCAL-Part val | mAP: 35.8 -> 38.2 | Helped |
| add object class to VGG16 part detector (ablation) | VGG16 part-appearance baseline with bounding-box regression · PASCAL-Part val | mAP: 35.8 -> 35.4 | Hurt |
| combine all object cues with VGG16 (ablation) | VGG16 part detector with bounding-box regression · PASCAL-Part val | mAP: 35.8 -> 40.1 | Helped |
Closest papers by meaning
- Beyond Holistic Object Recognition: Enriching Image Understanding With Part States (CVPR 2018 · similarity 0.91)
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery (NeurIPS 2026 · similarity 0.88)
- PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding (NeurIPS 2025 · similarity 0.87)
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.87)
- Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation (CVPR 2025 · similarity 0.86)
- The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding (CVPR 2024 · 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.