AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

CaT: Weakly Supervised Object Detection With Category Transfer

Tianyue Cao, Lianyu Du, Xiaoyun Zhang, Siheng Chen, Ya Zhang, Yan-Feng Wang

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 25 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 double-supervision mean teacher (DSMT) (ablation)weakly supervised mean teacher baseline · Pascal VOC 2007 test (COCO-65 source)mAP / CorLoc: 35.2 -> 60.3 mAP; 55.5 -> 77.8 CorLocImproved
add semantic graph convolutional network on top of DSMT (ablation)CaT · Pascal VOC 2007 test (COCO-65 source)mAP / CorLoc: 60.3 -> 63.0 mAP; 77.8 -> 80.0 CorLocImproved
increase the number of overlapping categories n (ablation)CaT · Pascal VOC 2007 testmAPImproved
remove images (not only annotations) of overlapping categories from COCO source (ablation)CaT · Pascal VOC 2007 testmAP / CorLoc: 58.0 -> 59.2 mAP; 73.8 -> 75.9 CorLocImproved
add 5 overlapping categories (COCO-65 instead of COCO-60) (ablation)CaT · Pascal VOC 2007 testmAP / CorLoc: 58.0 -> 63.5 mAP; 73.8 -> 80.3 CorLocImproved
add category transfer (CaT_0) vs best pure WSOD CASDCaT · Pascal VOC 2007 testmAP / CorLoc: 56.8 -> 58.0 mAP; 70.4 -> 73.8 CorLocImproved
CaT_0 vs previous transfer method Boosting (COCO-60)CaT · Pascal VOC 2007 testmAP / CorLoc: 55.2 -> 58.0 mAP; 72.4 -> 73.8 CorLocImproved
use similarity inter-dataset edges rather than hand-crafted edges (ablation)CaT · KITTI testmAP: 80.6 mAP with similarity edgesImproved
combine similarity and hand-crafted inter-dataset edges (ablation)CaT · KITTI testCorLoc: 58.9 CorLoc with both edgesMixed
vary fully-supervised loss weight lambda_full away from 0.5 (ablation)CaT · Pascal VOC 2007 testmAPHurt
increase graph threshold tau away from 0.4 (sparser graph) (ablation)CaT · Pascal VOC 2007 testmAPHurt

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