AI Paper Atlas

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

Grad-ECLIP: Gradient-Based Visual and Textual Explanations for CLIP

Chenyang Zhao, Kun Wang, Janet H. Hsiao, Antoni B. Chan

TPAMI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 14 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 loosened 0-1 normalized spatial weight lambda_i (ablation)Grad-ECLIP · ImageNet val (GT, top-1)IMD: 0.118 -> 0.137Improved
add loosened spatial weight lambda_i (ablation)Grad-ECLIP · MS COCO image explanation IR@1IMD: 0.001 -> 0.033Improved
add loosened spatial weight lambda_i (ablation)Grad-ECLIP · MS COCO text explanation IRIMD: 0.001 -> 0.076Improved
add loosened spatial weight lambda_i (ablation)Grad-ECLIP · ImageNet-SPoint Game: 0.8356 -> 0.8899Improved
add loosened spatial weight lambda_i (ablation)Grad-ECLIP · ImageNet-SmaskIoU: 0.3314 -> 0.2869Hurt
replace softmax attention with 0-1 normalized similarity as spatial weight (ablation)Grad-ECLIP · qualitative heat mapsexplanation qualityImproved
aggregate only the last layer instead of all 12 layers for image explanation (ablation)Grad-ECLIP image encoder · MS COCO IRIMD: -0.1465 -> 0.0330Improved
aggregate last 8 layers instead of 1 layer for text explanation (ablation)Grad-ECLIP text encoder · MS COCO IRIMD: -0.0059 -> 0.0296Improved
aggregate last 8 layers instead of all 12 for text explanation (ablation)Grad-ECLIP text encoder · MS COCO IRIMD: 0.0125 -> 0.0296Improved
use single attention head instead of multi-head for explanation (ablation)Grad-ECLIP · qualitative heat mapsexplanation focusImproved
use predicted class instead of ground-truth class as text promptGrad-ECLIP · ImageNet val top-1IMD: 0.137 -> 0.113Hurt
compare Grad-ECLIP with CLIPSurgery on insertionGrad-ECLIP vs CLIPSurgery · ImageNet val (GT, top-1)Insertion AUC: 0.384 vs 0.383No clear effect

Later papers that compared with this method

1 later accepted paper reports Grad-ECLIP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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