AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

LoA-Trans: Enhancing Visual Grounding by Location-Aware Transformers

Ziling Huang, Shin'ichi Satoh

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 1 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 TaskSyn Network for task information exchange in decoder (ablation)LoA-Trans-S · RefCOCO valmIoU: 74.58 -> 76.03Improved
add TaskSyn Network (ablation)LoA-Trans-S · RefCOCO valPr@0.5: 86.52 -> 87.59Improved
use query selection instead of random initialized queries (ablation)LoA-Trans-S · RefCOCO valmIoU: 75.67 -> 76.03Improved
use query selection instead of using all features as queries (ablation)LoA-Trans-S · RefCOCO valmemory: Out of Memory -> 87.59 Pr@0.5Improved
increase decoder layers from 3 to 6 (ablation)LoA-Trans-S · RefCOCO valPr@0.5: 87.20 -> 87.59Improved
increase decoder layers from 6 to 8 (ablation)LoA-Trans-S · RefCOCO valPr@0.5: 87.59 -> 86.76Hurt
increase selected queries K from 50 to 100 (ablation)LoA-Trans-S · RefCOCO valPr@0.5: 86.80 -> 87.59Improved
increase selected queries K from 100 to 125 (ablation)LoA-Trans-S · RefCOCO valPr@0.5: 87.59 -> 86.77Hurt
replace estimated center with ground-truth center (ablation)LoA-Trans-B · RefCOCO val, centerness [0.0,0.1)Pr@0.5: 10.95 -> 34.40Improved
use LoA-Trans-B instead of VG-LAW on RefCOCO+ testB segmentationVisual grounding · RefCOCO+ testB (RES)mIoU: 58.89 -> 62.90Improved
use LoA-Trans-S instead of VG-LAW on RefCOCO testB (REC)Visual grounding · RefCOCO testB (REC)Pr@0.5: 83.16 (VG-LAW) vs 82.98 (LoA-Trans-S)No clear effect

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