AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding

Wei Chen, Long Chen, Yu Wu

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 15 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
use transformer decoder instead of encoder for vision-language fusion (ablation)EEVG · RefCOCOg val(U) RECaccuracy (%): 78.43 -> 79.27Improved
use decoder instead of encoder for fusion (ablation)EEVG · runtime, 196 visual tokens, 300 linguistic tokensruntime (ms): 14.85 -> 8.09Improved
static token elimination instead of no elimination (ablation)EEVG · RefCOCOg RES valmIoU: 68.16 -> 66.38Hurt
dynamic token elimination instead of no elimination (ablation)EEVG · RefCOCOg RES valmIoU: 68.16 -> 68.89Improved
add adaptive spatial attention to dynamic elimination (ablation)EEVG · RefCOCOg RES valmIoU: 68.89 -> 69.15Improved
use efficient light mask head instead of FPN-like (ablation)EEVG · RefCOCOgparameters and RES val mIoU: 8.11M -> 0.79M params; 68.64 -> 69.15 mIoUImproved
add 1-channel convolution layer to mask head (ablation)EEVG mask head · RefCOCOg RES valmIoU: 67.71 -> 69.15Improved
EEVG versus prior methods on RefCOCOg (complex expressions)EEVG ViT-B · RefCOCOgaccuracy (%): +3.62% val, +3.93% testImproved
EEVG with pre-training on large corpus versus PolyFormer on RefCOCO+ RECEEVG · RefCOCO+ val REC (pre-trained)accuracy (%): 83.73 vs 82.24Hurt

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