AI Paper Atlas

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

Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP

Zhenzhang Ye, Duolikun Danier, Bo Zhao, Hakan Bilen

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP · 0 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 preliminary filtering (ablation)CDPS hybrid classifier · UCF101 (4-shot)accuracy (%): 71.05 -> 77.24Improved
add preliminary filtering (ablation)CDPS hybrid classifier · EuroSAT (4-shot)accuracy (%): 77.80 -> 80.89Improved
add preliminary filtering (ablation)CDPS hybrid classifier · FGVCAircraft (4-shot)accuracy (%): 38.47 -> 39.84Improved
add adaptive lambda combination instead of static 0.5 (ablation)CDPS hybrid classifier · FGVCAircraft (4-shot)accuracy (%): 32.52 -> 39.84Improved
add adaptive lambda combination instead of static 0.5 (ablation)CDPS hybrid classifier · StanfordCars (4-shot)accuracy (%): 86.87 -> 88.46Improved
add adaptive lambda combination instead of static 0.5 (ablation)CDPS hybrid classifier · UCF101 (4-shot)accuracy (%): 75.95 -> 77.24Improved
add the inter-class ambiguity term to the patch score (ablation)CDPS · DTD, Aircraft, Pets, Birds (4-shot)accuracy drop when removed: 3.07 average drop without interImproved
add the intra-class consistency term to the patch score (ablation)CDPS · DTD, Aircraft, Pets, Birds (4-shot)accuracy drop when removed: 4.67 average drop without intraImproved
use leave-one-out selected lambda instead of empirically optimal lambda (ablation)CDPS · 12 datasetsaccuracy (%): 0.47% average accuracy gap (0.81 at 2 shots, 0.32 at 16)No clear effect
increase number of discriminative patches K to 30 (ablation)CDPS · FGVCAircraftaccuracyNo clear effect
fuse features from layers 2, 6 and 12 via linear combinationCDPS · ImageNet-V2accuracy: +1.32%Improved
replace training-free baselines with CDPS in 8-shot ImageNet runtimeCDPS vs TIMO · ImageNettime (s): 305.7 -> 80.6Improved

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