AI Paper Atlas

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

Focus Your Attention when Few-Shot Classification

Haoqing Wang, Shibo Jie, Zhi-Hong Deng

NeurIPS 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class detection · 2 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 FORT (key-patch attention enhancement)LoRA, DINO ViT-B/16 · CUB 20-way 1-shotaccuracy (%): 57.9 -> 62.5Improved
add FORTLoRA, DINO ViT-B/16 · Cars 20-way 5-shotaccuracy (%): 64.3 -> 65.7Improved
add FORTFT, Swin-T/7 iBOT · CUB 20-way 1-shotaccuracy (%): 52.7 -> 59.1Improved
add FORTLoRA, CLIP ViT-B/16 · CUB 20-way 1-shotaccuracy (%): 86.3 -> 87.8Improved
add FORTLoRA, DINO ViT-B/16 · Aircraft 20-way 1-shotaccuracy (%): 26.0 -> 31.3Improved
add FORTLoRA, DINO ViT-B/16 · Pets 20-way 5-shotaccuracy (%): 89.8 -> 90.9Improved
add FORTFT, DINO ViT-B/16 · Pets 20-way 1-shotaccuracy (%): 71.6 -> 72.6No clear effect
add FORTLoRA, DINO ViT-B/16 · Attention-weighted importance, 1-shot supportimportance score (x10^-2): 0.71 -> 1.00Improved
fine-tune with LoRA instead of keeping backbone frozen (MetaOptNet)DINO ViT-B/16 · Cars 20-way 1-shotaccuracy (%): 24.1 -> 23.3Hurt
use only attention for position prompts instead of attention plus gradient (ablation)FORT with LoRA, DINO · CUB 20-way 1-shotaccuracy (%): 62.5 -> 62.1Hurt
use only gradient for position prompts instead of attention plus gradient (ablation)FORT with LoRA, DINO · CUB 20-way 1-shotaccuracy (%): 62.5 -> 60.0Hurt
use only attention for position prompts instead of attention plus gradient (ablation)FORT with LoRA, CLIP · CUB 20-way 1-shotaccuracy (%): 87.8 -> 86.6Hurt

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