AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Label Image Recognition by Recurrently Discovering Attentional Regions

Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, Liang Lin

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 339 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
use learned attentional regions from spatial transformer instead of five object proposals (ablation)recurrent memorized-attention model · PASCAL VOC 2007 test (single-crop 512)mAP: 88.6 -> 90.4Improved
add anchor, scale and positive constraints on the transformer (ablation)recurrent memorized-attention model · PASCAL VOC 2007 test (multi-crop 512)mAP: 89.9 -> 91.3Improved
add anchor constraint to scale + positive (ablation)attentional region constraints · PASCAL VOC 2007 test (multi-crop 512)mAP: 90.2 -> 91.3Improved
add scale constraint to anchor + positive (ablation)attentional region constraints · PASCAL VOC 2007 test (multi-crop 512)mAP: 90.3 -> 91.3Improved
add positive constraint to anchor + scale (ablation)attentional region constraints · PASCAL VOC 2007 test (multi-crop 512)mAP: 90.4 -> 91.3Improved
add the three region constraints (ablation)recurrent memorized-attention model · MS-COCO val (multi-crop 512, constraint ablation)mAP: 71.5 -> 72.2Improved
add the three region constraints (ablation)recurrent memorized-attention model · MS-COCO val (multi-crop 512, constraint ablation)C-F1: 65.8 -> 66.5Improved
add the three region constraints (ablation)recurrent memorized-attention model · MS-COCO val (multi-crop 512, constraint ablation)O-F1: 70.9 -> 71.3Improved
use ten-crop instead of single-crop at scale 512recurrent memorized-attention model · PASCAL VOC 2007 testmAP: 90.4 -> 91.3Improved
fuse two scales with ten-crop instead of one scalerecurrent memorized-attention model · PASCAL VOC 2007 testmAP: 91.3 -> 91.9Improved
fuse two scales with ten-crop instead of one scalerecurrent memorized-attention model · MS-COCO valmAP: 72.2 -> 73.4Improved
increase scale from 512 to 640 (single-crop)recurrent memorized-attention model · MS-COCO valmAP: 70.4 -> 70.5No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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