AI Paper Atlas

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

Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection

Keren Ye, Mingda Zhang, Adriana Kovashka, Wei Li, Danfeng Qin, Jesse Berent

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 47 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 text classifier label inference for unmatched captions (ablation)ExactMatch · VOC 2007 (COCO captions)mAP: 39.9 -> 43.1Improved
use text classifier instead of manual ExtendVocab synonyms (ablation)EM + ExtendVocab · VOC 2007 (COCO captions)mAP: 42.5 -> 43.1Improved
add GloVe pseudo labels (ablation)ExactMatch · VOC 2007 (COCO captions)mAP: 39.9 -> 40.5Improved
learn GloVe embeddings on COCO (ablation)EM + GloVePseudo · VOC 2007 (COCO captions)mAP: 40.5 -> 41.7Improved
add text classifier labels (ablation)ExactMatch · VOC 2007 (Flickr30K captions)mAP: 31.0 -> 33.6Improved
add manual ExtendVocab labels (ablation)ExactMatch · VOC 2007 (Flickr30K captions)mAP: 31.0 -> 29.3Hurt
add text classifier labels (ablation)ExactMatch · COCO test-devAP@0.5: 19.7 -> 20.2Improved
add GloVe pseudo labels (ablation)ExactMatch · COCO test-devAP@0.5: 19.7 -> 19.0Hurt
add OICR online refinement (1, 2, 3 times) (ablation)basic detection network · VOC 2007 (image-level labels)mAP: +24%, +29%, +30%Improved
use Inception-V2 based architecture instead of VGG_M (ablation)OICR with no refinement · VOC 2007 (image-level labels)mAP: +27%Improved
train text classifier on 100% instead of 5% of COCO (ablation)text classifier · COCO val label precisionprecision: 89% -> 92%No clear effect
increase caption training data to 1M samples (ablation)Cap2Det · VOC 2007 (Flickr data)mAP: 54.4 mAP at 1 million samples (extrapolated)Improved

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