AI Paper Atlas

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

Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding

Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Dechao Meng, Qingming Huang

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 101 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 adaptive reconstruction loss to language reconstruction (ablation)ARN · RefCLEF testaccuracy IoU>0.5 (%): 21.86 -> 25.35Improved
add attribute classification loss (ablation)ARN (L_lan+L_adp) · RefCLEF testaccuracy IoU>0.5 (%): 25.35 -> 26.19Improved
add attribute classification loss, lan weight 1 (ablation)ARN · RefCLEF valaccuracy IoU>0.5 (%): 22.34 -> 25.35Improved
raise language reconstruction weight gamma from 10 to 30 (ablation)ARN · RefCLEF valaccuracy IoU>0.5 (%): 24.34 -> 26.19Improved
raise language reconstruction weight gamma from 30 to 40 (ablation)ARN · RefCLEF valaccuracy IoU>0.5 (%): 26.19 -> 25.53Hurt
raise adaptive visual reconstruction weight alpha from 0.001 to 0.01 (ablation)ARN · RefCLEF valaccuracy IoU>0.5 (%): 24.14 -> 21.83Hurt
raise gamma from 5 to 15 (ablation)ARN · RefCOCO testAaccuracy IoU>0.5 (%): 36.01 -> 27.13Hurt
replace adaptive loss with language reconstruction loss (ablation)ARN (L_adp+L_att vs L_lan+L_att) · RefCOCO testBaccuracy IoU>0.5 (%): 29.09 -> 36.47Improved
replace language loss with adaptive loss (ablation)ARN (L_lan+L_att vs L_adp+L_att) · RefCOCO testAaccuracy IoU>0.5 (%): 35.27 -> 36.43Mixed
use detected Faster R-CNN proposals instead of ground-truth boxes (ablation)ARN · RefCOCO valaccuracy IoU>0.5 (%): 34.26 -> 32.17Hurt
full ARN versus previous best KAC NetARN · RefCLEF testaccuracy IoU>0.5 (%): 15.83 -> 26.19Improved
language reconstruction only versus previous bestARN (L_lan) · RefCLEF testaccuracy IoU>0.5 (%): 15.83 -> 21.86Improved

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