Research map / Detection and segmentation / Open-set and few-shot detection
Unsupervised Object-Level Representation Learning from Scene Images
Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew-Soon Ong, Chen Change Loy
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 |
|---|---|---|---|
| add intra-RoI loss (ablation) | ORL · VOC07 | mAP: 84.5 -> 85.7 | Improved |
| add inter-RoI loss (ablation) | ORL · VOC07 | mAP: 84.5 -> 85.9 | Improved |
| add both intra-RoI and inter-RoI losses (ablation) | ORL · VOC07 | mAP: 84.5 -> 86.7 | Improved |
| increase nearest neighbors K from 1 to 10 (ablation) | ORL · VOC07 | mAP: 84.7 -> 86.7 | Improved |
| increase nearest neighbors K from 10 to 20 (ablation) | ORL · VOC07 | mAP: 86.7 -> 87.0 | Improved |
| vary RoI pairs N from 5% to 10% to 20% (ablation) | ORL · VOC07 | mAP: 86.1 -> 86.7 -> 86.4 | No clear effect |
| add four extra 96x96 crops to BYOL (multi-crop) (ablation) | BYOL · VOC07 | mAP: 84.5 -> 84.0 | Hurt |
| object-level ORL vs multi-crop BYOL with same views (ablation) | ORL · VOC07 | mAP: 84.0 -> 86.7 | Improved |
| replace selective search boxes with COCO ground-truth boxes (ablation) | ORL · VOC07 | mAP: 86.7 -> 85.4 | Hurt |
| pre-training schedule 100 to 1600 epochs (ablation) | ORL vs BYOL · VOC07 | mAP: 83.5 -> 87.1 | Improved |
| ORL at 200 epochs vs BYOL at 1600 epochs (ablation) | ORL · VOC07 | mAP: 84.9 -> 85.2 | Improved |
| ORL vs BYOL pre-trained on COCO (ablation) | ORL · Places205 linear | top-1: 50.5 -> 52.7 | Improved |
Closest papers by meaning
- Object Discovery and Representation Networks (ECCV 2022 · similarity 0.89)
- Self-Supervised Learning of Object Parts for Semantic Segmentation (CVPR 2022 · similarity 0.89)
- Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations (ICLR 2023 · similarity 0.88)
- Revisiting Self-Supervised Visual Representation Learning (CVPR 2019 · similarity 0.88)
- Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning (CVPR 2021 · similarity 0.88)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · 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.
