AI Paper Atlas

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

Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding

Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Zechao Li, Qi Chuan Tian, Qingming Huang

TPAMI 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 59 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 entity enhancement and soft context pooling to ARN (EARN vs ARN)ARN · RefCOCOg valaccuracy (IoU>0.5): + 10.67%Improved
add entity enhancement and adaptive reconstruction vs IGN+CCLweak-supervised REG · RefCOCO testBaccuracy (IoU>0.5): 32.59 -> 38.59Improved
add entity enhancement (selects candidate proposals) (ablation)EARN on RefCLEF · RefCLEF valaccuracy (IoU>0.5): 26.19 -> 36.68Improved
add adaptive reconstruction on top of language reconstruction (ablation)EARN on RefCLEF · RefCLEF valaccuracy (IoU>0.5): 21.86 -> 25.35Improved
add attribute classification (ablation)EARN on RefCLEF · RefCLEF valaccuracy (IoU>0.5): 25.35 -> 26.19Improved
add adaptive reconstruction to entity-enhanced model (ablation)EARN · RefCOCO testBaccuracy (IoU>0.5): 36.98 -> 38.59Hurt
add adaptive reconstruction to entity-enhanced model (ablation)EARN · RefCOCOg valaccuracy (IoU>0.5): 38.37 -> 45.33Improved
use soft-context pooling instead of max-context pooling (ablation)EARN · RefCOCOg valaccuracy (IoU>0.5): 42.81 -> 45.33Improved
use soft-context pooling instead of max-context pooling on complex relationships (ablation)EARN · RefCOCOg val (complex)accuracy (IoU>0.5): 43.11 -> 46.47Improved
use hard subject filter instead of soft subject filter (ablation)EARN · RefCOCOg valaccuracy (IoU>0.5): 38.45 -> 40.24Improved
add location features to attribute features (ablation)EARN · RefCOCO valaccuracy (IoU>0.5): 15.58 -> 36.47Improved
add context features (ablation)EARN · RefCOCO+ valaccuracy (IoU>0.5): 20.33 -> 36.49Improved

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