Training-Free Few-Shot Image Classification via Diagnostic Verification and Bounded Correction

Training-free adaptation of CLIP has become a promising paradigm for few-shot image classification because it avoids gradient optimization and overfitting. Existing methods typically construct visual and textual classifiers independently and fuse them with globally fixed weights, implicitly assuming that all samples share the same optimal fusion weight. This assumption fails in few-shot settings: when the top-2 logits are close, fixed weights cannot resolve ambiguity, while unbounded z-score correction may over-correct ambiguous samples. We propose DiVe, a Diagnostic Verification and Bounded Correction framework. For each sample, DiVe verifies its top-2 candidates, constructs a discriminative direction from fine-grained textual prototypes, projects test features and visual prototypes onto this direction to quantify attribution, and converts verification confidence into a bounded correction signal via a tanh mapping. DiVe is fully training-free and can be plugged into existing training-free CLIP classifiers as post-processing. On 11 datasets with 4 CLIP backbones under the 16-shot setting, DiVe achieves the best average accuracy among training-free methods, reaching 76.43% with ResNet-50, and improves GDA-CLIP by 0.92% and TIMO by 0.51% on six representative datasets. Cross-dataset experiments on ImageNet variants demonstrate robustness under distribution shift, while also revealing boundary conditions under extreme domain gaps.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-20
DOI
https://doi.org/10.21203/rs.3.rs-11133832/v1
Primary Topic
Domain Adaptation and Few-Shot Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Training-Free Few-Shot Image Classification via Diagnostic Verification and Bounded Correction

Rui Fang, Lei Chen, Li Duan, HongPing Zhang
3 links
Research Square
Domain Adaptation and Few-Shot Learning
preprint

Training-Free Few-Shot Image Classification via Diagnostic Verification and Bounded Correction

Rui Fang, Lei Chen, Li Duan, HongPing Zhang
preprint en

Abstract

Training-free adaptation of CLIP has become a promising paradigm for few-shot image classification because it avoids gradient optimization and overfitting. Existing methods typically construct visual and textual classifiers independently and fuse them with globally fixed weights, implicitly assuming that all samples share the same optimal fusion weight. This assumption fails in few-shot settings: when the top-2 logits are close, fixed weights cannot resolve ambiguity, while unbounded z-score correction may over-correct ambiguous samples. We propose DiVe, a Diagnostic Verification and Bounded Correction framework. For each sample, DiVe verifies its top-2 candidates, constructs a discriminative direction from fine-grained textual prototypes, projects test features and visual prototypes onto this direction to quantify attribution, and converts verification confidence into a bounded correction signal via a tanh mapping. DiVe is fully training-free and can be plugged into existing training-free CLIP classifiers as post-processing. On 11 datasets with 4 CLIP backbones under the 16-shot setting, DiVe achieves the best average accuracy among training-free methods, reaching 76.43% with ResNet-50, and improves GDA-CLIP by 0.92% and TIMO by 0.51% on six representative datasets. Cross-dataset experiments on ImageNet variants demonstrate robustness under distribution shift, while also revealing boundary conditions under extreme domain gaps.

Research Square
Naval University of Engineering (CN)
Domain Adaptation and Few-Shot Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon