AI Paper Atlas

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

No Token Left Behind: Explainability-Aided Image Classification and Generation

Roni Paiss, Hila Chefer, Lior Wolf

ECCV 2022 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 27 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 explainability loss to CoOp prompt learning (ablation)CoOp (CLIP ViT-B/16) · ImageNet 1-shot unifiedtop-1 accuracy (%): 66.93 -> 67.62 (M=4); 63.66 -> 67.09 (M=16)Improved
add explainability loss to CoOp prompt learning (class-specific) (ablation)CoOp (CLIP ViT-B/16) · ImageNet 1-shot CSCtop-1 accuracy (%): 46.20 -> 48.74Improved
add explainability loss to CoOp prompt learning (ResNet-50) (ablation)CoOp (CLIP ResNet-50) · ImageNet-A 1-shot unifiedtop-1 accuracy (%): 21.43 -> 22.74Improved
few-shot CoOp and linear probing instead of manual 0-shot promptsCLIP ResNet-50 · ImageNet 1-shot unifiedtop-1 accuracy (%): 58.18 -> 54.45 (CoOp M=16); 58.18 -> 21.70 (LP)Hurt
use class name at end of prompt with explainability loss (ablation)CoOp (ResNet-50) · ImageNet 1-shottop-1 accuracy (%): 53.41 -> 57.78Improved
add explainability loss in 2-shot setting (ablation)CoOp (ResNet-50) · ImageNet 2-shottop-1 accuracy (%): 56.70 -> 58.42Improved
add explainability loss in 4-shot setting (ablation)CoOp (ViT-B/16) · ImageNet 4-shottop-1 accuracy (%): 68.20 -> 68.90Improved
add explainability loss to StyleCLIP latent optimizationStyleCLIP · user study prompt 'A man with a beard'quality rating (1-5): 2.92 -> 4.28Improved
add explainability loss to StyleCLIP latent optimizationStyleCLIP · user study prompt 'A man with a beard'identity preservation rating (1-5): 3.61 -> 2.23Hurt
add explainability loss to StyleCLIP latent optimizationStyleCLIP · user study prompt 'A person with purple hair'identity preservation rating (1-5): 4.13 -> 3.51Hurt
use explainability IoU loss instead of similarity-based masked CLIP lossCLIP-guided VQGAN · MSCOCO spatial conditioningAP (%): 8 -> 26.2Improved
use explainability IoU loss instead of similarity-based lossCLIP-guided VQGAN · MSCOCO spatial conditioningprecision (%): 46.4 -> 71.7Improved

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