Research map / Detection and segmentation / CNN features
Adaptive Object Detection Using Adjacency and Zoom Prediction
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 |
|---|---|---|---|
| use adaptive region search with AZ-Net proposals instead of RPN proposals | Fast R-CNN detection pipeline · VOC 2007 test | mAP: 69.9 -> 70.2 | Helped |
| use unshared convolutional features (ablation) | AZ-Net · VOC 2007 test | mAP: 70.2 -> 70.4 | Helped |
| use adaptive region search with AZ-Net proposals instead of RPN proposals | Fast R-CNN detection pipeline · MSCOCO 2015 test-dev | AP: 21.9 -> 22.3 | Helped |
| use adaptive region search with AZ-Net proposals instead of RPN proposals | Fast R-CNN detection pipeline · MSCOCO 2015 test-dev | AP IoU=0.50: 42.7 -> 41.0 | Hurt |
| use adaptive AZ-Net search rather than fixed RPN anchors | region proposal generation · VOC 2007 test | recall at IoU threshold 0.5: reaches 0.6 recall with only 10 proposals | Helped |
| use adaptive AZ-Net search rather than fixed RPN anchors | region proposal generation · VOC 2007 test small objects | recall at IoU threshold 0.5 | Helped |
Closest papers by meaning
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.89)
- Sparse R-CNN: End-to-End Object Detection With Learnable Proposals (CVPR 2021 · similarity 0.89)
- Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks (AAAI 2019 · similarity 0.88)
- Dynamic Zoom-In Network for Fast Object Detection in Large Images (CVPR 2018 · similarity 0.88)
- Unsupervised Object Detection with Theoretical Guarantees (NeurIPS 2024 · similarity 0.86)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (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.