AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

LICO: Explainable Models with Language-Image COnsistency

Yiming Lei, Zilong Li, Yangyang Li, Junping Zhang, Hongming Shan

NeurIPS 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class detection · 5 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 LICOResNet-50 · ImageNet-1k top-1accuracy (%): 76.13 -> 76.27Improved
add GCCResNet-50 · ImageNet-1k top-1accuracy (%): 76.13 -> 74.40Hurt
add CGCResNet-50 · ImageNet-1k top-1accuracy (%): 76.13 -> 74.60Hurt
add LICOViT-Base-16 · ImageNet-1k accuracyaccuracy (%): 77.9 -> 78.2Improved
add LICOGrad-CAM · ImageNet insertionInsertion AUC: 53.5 -> 57.1Improved
add LICOGroup-CAM · ImageNet insertionInsertion AUC: 56.8 -> 55.2Hurt
add LICOGrad-CAM · ImageNet deletionDeletion AUC: 13.3 -> 15.1Hurt
add LICO with 40 labelsWRN · CIFAR-10accuracy (%): 23.4 -> 24.9Improved
add LICOPARN18 · CIFAR-100 2500 labelsaccuracy (%): 23.7 -> 21.4Hurt
add LICOWRN · CIFAR-100 fullaccuracy (%): 80.9 -> 82.2Improved
use only L_OT without L_MM (ablation)LICO · ImageNet top-1accuracy (%): 76.27 -> 75.98Hurt
use 12 context tokens instead of 0 (ablation)LICO · ImageNet top-1accuracy (%): 75.64 -> 76.27Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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