AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Context Disentangling and Prototype Inheriting for Robust Visual Grounding

Wei Tang, Liang Li, Xuejing Liu, Lu Jin, Jinhui Tang, Zechao Li

TPAMI 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 56 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 Hadamard fusion instead of Vision-Language Transformer fusion (ablation)TransCP · ReferIt test (trained on RefCOCO)top-1 accuracy: 24.24 -> 27.71Improved
use Hadamard fusion instead of Vision-Language Transformer fusion (ablation)TransCP · RefCOCO valtop-1 accuracy: 83.02 -> 84.25Improved
add linguistic disentangling to baseline (ablation)TransVG · RefCOCO valtop-1 accuracy: 80.48 -> 82.46Improved
add visual disentangling to baseline (ablation)TransVG · RefCOCO valtop-1 accuracy: 80.48 -> 84.47Improved
add prototype module alone to baseline (ablation)TransVG · RefCOCO valtop-1 accuracy: 80.48 -> 81.48No clear effect
add Hadamard fusion to baseline (ablation)TransVG · RefCOCO valtop-1 accuracy: 80.48 -> 82.90Improved
add linguistic disentangling to Hadamard fusion (ablation)TransCP · ReferIt testtop-1 accuracy: 24.19 -> 26.59Improved
add visual disentangling on top of H.D. and L.D. (ablation)TransCP · ReferIt valtop-1 accuracy: 27.27 -> 28.53Mixed
add prototype discovering and inheriting to H.D.+L.D.+V.D. (ablation)TransCP · ReferIt testtop-1 accuracy: 27.11 -> 27.71Improved
add prototype discovering and inheriting to H.D.+L.D.+V.D. (ablation)TransCP · RefCOCO valtop-1 accuracy: 83.90 -> 84.25Improved
vary prototype bank size (too small or too large) (ablation)TransCP · ReferIt open-vocabularytop-1 accuracyMixed
number of regression Transformer encoder layers (ablation)TransCP · RefCOCO and ReferIttop-1 accuracyMixed

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