AI Paper Atlas

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

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 26 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace default dilations with learned fixed dilations (FD)Faster R-CNN R50-C4 · COCO minivalAP: 35.4 -> 38.4Improved
replace default dilations with learned fixed dilations (FD)Faster R-CNN R101-C4 · COCO minivalAP: 38.7 -> 40.9Improved
replace default dilations with learned fixed dilations (FD)Faster R-CNN R50-FPN · COCO minivalAP: 36.2 -> 37.9Improved
replace default dilations with learned fixed dilations (FD)Faster R-CNN R101-FPN · COCO minivalAP: 38.6 -> 40.1Improved
replace default dilations with learned fixed dilations (FD)RetinaNet R50-FPN · COCO minivalAP: 36.0 -> 37.5Improved
replace default dilations with learned fixed dilations (FD)RetinaNet R101-FPN · COCO minivalAP: 37.5 -> 38.8Improved
use FD network instead of dynamic GSL network (ablation)Faster R-CNN R50-C4 · COCO minivalAP: 38.7 -> 38.4No clear effect
use FD network instead of dynamic GSL network (ablation)Faster R-CNN R101-C4 · COCO minivalAP: 40.7 -> 40.9No clear effect
use FD network instead of dynamic GSL network (ablation)Faster R-CNN R50-C4 · inference timems: 269ms -> 159msImproved
use FD network instead of dynamic GSL network (ablation)RetinaNet R50-FPN · COCO minivalAP: 38.0 -> 37.5Hurt
fine-tune FD from GSL weights (WT) with 1x instead of FD 2x from ImageNet (ablation)Faster R-CNN R50-C4 · COCO minivalAP: 39.6 -> 40.0Improved
fine-tune FD from GSL weights (WT) with 1x instead of FD 2x from ImageNet (ablation)RetinaNet R50-FPN · COCO minivalAP: 37.8 -> 38.3Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy