AI Paper Atlas

Research map / Detection and segmentation / CNN features

Aggregation With Feature Detection

Shuyang Sun, Xiaoyu Yue, Xiaojuan Qi, Wanli Ouyang, Victor Adrian Prisacariu, Philip H.S. Torr

ICCV 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 5 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 DEPLA moduleResNet-50 · ImageNet-1k val (standard training)top-1 accuracy: 76.9 -> 78.6 (+1.6)Improved
add DEPLA moduleSEResNet-50 · ImageNet-1k val (standard training)top-1 accuracy: 77.5 -> 79.1Improved
add DEPLA module plus better training strategyResNet-50 · ImageNet-1k valtop-1 accuracy: 76.2 -> 80.6Improved
add DEPLA to well-tuned SEResNet-50++SEResNet-50++ · ImageNet-1k valtop-1 accuracy: 79.4 -> 81.3Improved
add DEPLA moduleSEResNet-101 · ImageNet-1k valtop-1 accuracy: 77.7 -> 82.1Improved
use adaptive BFN instead of plain BFN (ablation)ResNet-50-DEPLA · ImageNet-1k valtop-1 accuracy: 78.6 -> 78.8Improved
replace FPN with FPN-DEPLAMask R-CNN ResNet50 · COCO val2017box AP: 38.0 -> 39.0Improved
lower softmax temperature T from 1.0 to 0.2 (ablation)FPN-DEPLA · COCO val2017small-object AP: 23.5 -> 23.8Improved
vary softmax temperature T (ablation)FPN-DEPLA · COCO val2017box AP: 38.9 / 39.1 / 39.0No clear effect
add DEPLA to FishNet150 backboneFaster R-CNN FPN · COCO val2017box AP: 40.6 -> 43.1Improved
add DEPLA to FishNet150 backboneMask R-CNN · COCO val2017mask AP: 37.0 -> 39.4Improved
add DEPLA to FishNet150 backboneMask R-CNN · COCO val2017box AP: 41.5 -> 44.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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