AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning In Vision Transformers

Wenwen Liao, Hang Ruan, Jianbo Yu, Bing Song, Yuansong Wang, Xiaofeng Yang

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation · 1 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 projection layer in Active Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 51.15 -> 80.13Improved
add trainable prompt Pi (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 39.36 -> 80.13Improved
add MLP in Active Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 55.09 -> 80.13Improved
add attention in Active Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 75.98 -> 80.13Improved
add Combine Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 75.55 -> 80.13Improved
add Combine Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 5-shotaccuracy (%): 88.60 -> 88.81No clear effect
add F_att to Combine Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 5-shotaccuracy (%): 89.71 -> 88.81 (5-shot); 78.31 -> 80.13 (1-shot)Mixed
add SQ Attention Block (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 75.42 -> 80.20Improved
use conditional weights instead of simple average in aggregation (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 69.58 -> 80.13Improved
use fixed weights instead of simple average in aggregation (ablation)EfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 69.58 -> 69.97No clear effect
use EfficientFSL instead of LoRAEfficientFSL (ViT-B/16 21K) · FC100 5-way 1-shotaccuracy (%): 74.19 -> 80.13Improved
use EfficientFSL instead of full fine-tuning ViT-SEfficientFSL (ViT-S) · FC100 5-way 1-shotaccuracy (%): 52.93 -> 69.94Improved

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