Research map / Detection and segmentation / CNN features
POD: Practical Object Detection With Scale-Sensitive Network
Junran Peng, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, Junjie Yan
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 |
|---|---|---|---|
| replace default dilations with learned fixed dilations (FD) | Faster R-CNN R50-C4 · COCO minival | AP: 35.4 -> 38.4 | Improved |
| replace default dilations with learned fixed dilations (FD) | Faster R-CNN R101-C4 · COCO minival | AP: 38.7 -> 40.9 | Improved |
| replace default dilations with learned fixed dilations (FD) | Faster R-CNN R50-FPN · COCO minival | AP: 36.2 -> 37.9 | Improved |
| replace default dilations with learned fixed dilations (FD) | Faster R-CNN R101-FPN · COCO minival | AP: 38.6 -> 40.1 | Improved |
| replace default dilations with learned fixed dilations (FD) | RetinaNet R50-FPN · COCO minival | AP: 36.0 -> 37.5 | Improved |
| replace default dilations with learned fixed dilations (FD) | RetinaNet R101-FPN · COCO minival | AP: 37.5 -> 38.8 | Improved |
| use FD network instead of dynamic GSL network (ablation) | Faster R-CNN R50-C4 · COCO minival | AP: 38.7 -> 38.4 | No clear effect |
| use FD network instead of dynamic GSL network (ablation) | Faster R-CNN R101-C4 · COCO minival | AP: 40.7 -> 40.9 | No clear effect |
| use FD network instead of dynamic GSL network (ablation) | Faster R-CNN R50-C4 · inference time | ms: 269ms -> 159ms | Improved |
| use FD network instead of dynamic GSL network (ablation) | RetinaNet R50-FPN · COCO minival | AP: 38.0 -> 37.5 | Hurt |
| fine-tune FD from GSL weights (WT) with 1x instead of FD 2x from ImageNet (ablation) | Faster R-CNN R50-C4 · COCO minival | AP: 39.6 -> 40.0 | Improved |
| fine-tune FD from GSL weights (WT) with 1x instead of FD 2x from ImageNet (ablation) | RetinaNet R50-FPN · COCO minival | AP: 37.8 -> 38.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- Cascade R-CNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · better on 0 of 1 shared result
- CornerNet — CornerNet: Detecting Objects as Paired Keypoints (ECCV 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- An Analysis of Scale Invariance in Object Detection SNIP (CVPR 2018 · similarity 0.90)
- Scale Normalized Image Pyramids with AutoFocus for Object Detection (TPAMI 2021 · similarity 0.89)
- ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector (CVPR 2023 · similarity 0.88)
- Scale-Aware Trident Networks for Object Detection (ICCV 2019 · similarity 0.88)
- Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (ECCV 2020 · similarity 0.88)
- SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection (ECCV 2018 · similarity 0.88)
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.
