AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Region Features for Object Detection

Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, Jifeng Dai

ECCV 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 90 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
add appearance feature term to the geometric term (ablation)learned region feature module · COCO minivalmAP: 33.2 -> 34.1Improved
enlarge support region from 1x RoI to whole image (ablation)learned region feature module · COCO minivalmAP: 33.4 -> 34.3Improved
enlarge support region from 1x RoI to 2x RoI (ablation)regular RoI pooling · COCO minivalmAP: 29.8 -> 30.1No clear effect
enlarge support region from 1x RoI to 2x RoI (ablation)aligned RoI pooling · COCO minivalmAP: 32.9 -> 32.8No clear effect
use sparse sampling (196 outside, 14^2 inside) instead of dense enumeration (ablation)learned region feature module · COCO minivalmAP: 34.2 -> 34.1No clear effect
sparse sampling with 196 maximum outside positions instead of 100 (ablation)learned region feature module · COCO minivalmAP: 33.8 -> 34.1Improved
increase maximum inside sampling positions from 7^2 to 14^2 (ablation)learned region feature module · COCO minivalmAP: 33.4 -> 34.2Improved
replace regular RoI pooling by learned region feature moduleFaster R-CNN + ResNet-50 · COCO minivalmAP: 29.8 -> 33.4Improved
replace aligned RoI pooling by learned region feature moduleFaster R-CNN + ResNet-50 · COCO minivalmAP: 32.9 -> 33.4Improved
replace deformable RoI pooling by learned region feature moduleFaster R-CNN + ResNet-101 · COCO test-devmAP: 36.4 -> 36.4No clear effect
replace deformable RoI pooling by learned region feature moduleFPN + ResNet-101 · COCO test-devmAP: 40.0 -> 39.9No clear effect
replace aligned RoI pooling by learned region feature moduleFPN + ResNet-101 · COCO test-devmAP: 39.1 -> 39.9Improved

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