Few-Shot Image Classification

Follow this topic Ask about this topic

Few-shot image classification studies how to identify new visual categories when labeled examples are scarce, a common constraint in specialized or costly-to-annotate settings. Methods include episodic metric learning with prototypes, transfer from pretrained visual and vision-language models, prompt or adapter tuning, and synthetic data augmentation. Recent work also uses unlabeled query images for transductive refinement and applies these approaches to fine-grained, medical, agricultural, and remote-sensing images. A central tension is whether adaptation improves performance without overfitting tiny support sets or losing robustness to domain shift; pretraining overlap and reliable validation remain important concerns.

Latest papers

71 papers9 papers in the last four weeks, down 10% on the four weeks before. 0.1% of all new papers.

LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation
Oct 26, 2026Pavodi Maniamfu, Vogel Kiketa, Zezina Kuzulu Kuetu +4VLM Adaptation Few-Shot Image Classification
Temple University Japan Campus · Universit´e de Kinshasa · Universit´e Protestante au Congo +2
Component Pooling Trained Across Orientations for Few-Shot Remote Sensing Scene Classification
Oct 24, 2026Bingchen Yan, Wenheng Guo, Yuye ZhouRemote Sensing Scene Classification Few-Shot Image Classification
School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, 541004, China · School of Information Engineering, Institute of Disaster Prevention, Langfang, 065201, China · School of Computing & Technology, Asia Pacific University of Technology & Innovation, Kuala Lumpur, 57000, Malaysia
Depth-guided Geometric Adaptation for Few-shot Image Classification
Oct 20, 2026Zhiqi Miao, Estefanía Talavera, Weichuan Zhang +1Few-Shot Image Classification Few-Shot Learning
University of Groningen · University of Twente · Shanxi University of Science and Technology
EGiME: Entropy-Guided Model Evaluation in Few-Shot Learning
Oct 19, 2026Dequan Jin, Tao Li, Lifeng Xing +2Model Selection Few-Shot Learning
Department of Mathematics and Applied Mathematics, School of Mathematics and Information Science, Guangxi University, Nanning, Guangxi, 530004, China · Department of Mathematics, School of Science, Shanghai University, Shanghai, 200444, China · School of Economics, Guangxi University, Nanning, Guangxi, 530004, China
Cross-polarization pairing for label-free few-shot thin-section classification
Oct 17, 2026Bingchen YanFew-Shot Image Classification Microscopy Image Analysis
School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, 541004, China
LAMP: Layerwise Adaptive Mixing of Predictors for Training-Free Few-Shot Vision-Language Adaptation
Oct 15, 2026Zhipeng Ye, Feng Jiang, Qiufeng Wang +1Few-Shot Learning Few-Shot Image Classification
Taizhou Institute of Science and Technology, Nanjing University of Science and Technology, Taizhou 225300, Jiangsu, China · Department of Intelligence Science, Xi’an Jiaotong-Liverpool University, Suzhou 215123, Jiangsu, China · School of Computer Science and Technology, University of Arizona, Tucson 85705, AZ, USA
DVLA-RL++: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
Oct 8, 2026Wenhao Li, Xianjing Meng, Qiangchang Wang +3Few-Shot Learning Few-Shot Image Classification
School of Software, Shandong University, Jinan 250101, China · Shenzhen Loop Area Institute, Shenzhen 518038, China · School of Computer and Artificial Intelligence, Shandong University of Finance and Economics, Jinan 250014, China +1
FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification
Oct 7, 2026Ankita Das, Ambarish Parthasarathy, Sumohana S. Channappayya +1Few-Shot Image Classification Multimodal Federated Learning
Department of Computer Science and Engineering Indian Institute of Technology Hyderabad · Department of Artificial Intelligence Indian Institute of Technology Hyderabad · Department of Electrical Engineering Indian Institute of Technology Hyderabad
Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning
Sep 30, 2026Hongwei Zhao, Rui Liu, Yansong Liu +2Class-Incremental Learning Low-Rank Adaptation
School of Computer Science and Engineering, Beihang University · School of Computer Science, Beijing University of Posts and Telecommunications
Reprogramming Vision-Language Models via Structured Prompt Reparameterization
Sep 29, 2026Zizhao Li, Chengyi Cai, Mohammed Yaqoob Ansari +3VLM Adaptation Few-Shot Image Classification
The University of Melbourne, Melbourne, Australia
Prompt-Anchored Residual Adaptation for Biomedical Vision-Language Models
Sep 27, 2026Jingxuan Kang, Qianying Yue, Che Liu +1VLM Adaptation Few-Shot Learning
Imperial College London · The Chinese University of Hong Kong
Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images
Sep 25, 2026Tiffanie Godelaine, Manon Dausort, Karim El Khoury +3Histopathology Image Classification Few-Shot Image Classification
ICTEAM, Universit´e Catholique de Louvain, Belgium
Query-Conditioned Prototype Adaptation for Cross-Domain Few-Shot Learning: Single-Query Inference, Controlled Comparisons, and Failure Modes
Sep 25, 2026Rushab Rasik Karania, Tomas MaulSource-Free Cross-Domain Few-Shot Learning Few-Shot Learning
School of Computer Science, University of Nottingham Malaysia, Semenyih, 43500, Selangor, Malaysia
Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification
Sep 20, 2026Fahim Rahman, S. M. Tanjeeb Meheran Rohan, Md. Taimum Ibne Sayed +2Few-Shot Learning Spectral Methods
Department of Computer Science and Engineering Islamic University of Technology Gazipur, Bangladesh
ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning
Sep 16, 2026Neeraj YadavFew-Shot Image Classification Data-Efficient Learning
Independent Researcher, Uttar Pradesh, India
CALIPER: Metric-Grounded Model-Free Recognition of Visually Similar Industrial Parts
Sep 15, 2026Alankrit Gupta, Chenxi Tao, Seung-Kyum ChoiFine-Grained Image Classification Few-Shot Image Classification
George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology Atlanta, GA, U.S.A.
ProtoCAM: Interpretable Few-Shot Mask-Guided Prototypical Learning for Breast Lesion Classification in Ultrasound Imaging
Sep 11, 2026Ashkan EbadiMedical Image Classification Few-Shot Image Classification
Digital Technologies Research Centre National Research Council Canada Toronto, ON M5T 3J1
Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions
Sep 9, 2026Alejandro Galan-Cuenca, Marcelo Saval-Calvo, Antonio Javier GallegoDomain Adaptation Few-Shot Learning
University Institute for Computer Research, University of Alicante, Alicante, Spain
Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification
Sep 3, 2026Ruiling Liu, Linyue Zhang, Wenyi Zeng +5Frequency-Domain Feature Learning Fine-Grained Image Classification
Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
Aug 31, 2026Tiffanie Godelaine, Maxime Zanella, Karim El Khoury +2Computational Pathology Conditional Random Fields
Institute of Information and Communication Technologies, Electronics, and Applied Mathematics (ICTEAM), Université catholique de Louvain (UCLouvain), 1348 Louvain-la-Neuve, Belgium
Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets
Aug 19, 2026Ting Xiang, Chenxi Deng, Jinhui Zhao +4Data Augmentation Synthetic Data Augmentation
Hunan University
When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning
Aug 7, 2026Wei Liu, Xing Deng, Haijian ShaoSource-Free Cross-Domain Few-Shot Learning Few-Shot Domain Adaptation
College of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China
Locally Consistent Transductive Information Maximization for Few-Shot Remote Sensing Scene Classification
Jul 31, 2026Karim El Khoury, Benoît Gérin, Benoît Macq +1Remote Sensing Image Understanding Vision Foundation Model Adaptation
ICTEAM, UCLouvain, Louvain-la-Neuve, Belgium
Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning
Jul 24, 2026Haichen Zhou, Yazhe Lyu, Yixiong Zou +2Class-Incremental Learning Incremental Learning
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning
Jul 14, 2026Yumiao Zhao, Bo Jiang, Min Lu +2VLM Adaptation Quantum Machine Learning
Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China · Origin Quantum Computing Company Limited, Hefei, Anhui 230026, China
Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs
Jul 12, 2026Shubham RaoCoT Distillation VLM Adaptation
Entropy AI Research Labs Private Limited
TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
Jul 10, 2026Tianyou Jiang, Ziyu ZhouFew-Shot Domain Adaptation Logit Adjustment
University of Bern, Bern, Switzerland · Shanghai Jiao Tong University, Shanghai, China
Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition
Jul 7, 2026Xinda Liu, Qinyu Zhang, Weiqing Min +2VLM Adaptation Fine-Grained Image Classification
School of Information Science and Technology, Northwest University, Xi’an, Shaanxi, China · Laboratory of Intelligent Information Processing, Institute of Computing Technology, Beijing, China
AdaBoosting Text Prompts for Vision-Language Models
Jul 1, 2026Seokhee Jin, Changhwan Sung, Sunung Mun +2Vision-Language Models Ensemble Learning
KT Corporation, Republic of Korea · Pohang University of Science and Technology (POSTECH), Republic of Korea · National AI Research Lab, Republic of Korea
Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners
Jun 30, 2026Yunhan Wang, Eshika Khandelwal, Edson Araujo +3Multimodal Large Language Models Few-Shot Prompting
Tuebingen AI Center, University of Tuebingen, Germany

Oct 26, 2026J/K move · Enter open · S save

LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation

Pavodi Maniamfu, Vogel Kiketa, Zezina Kuzulu Kuetu, Jakin Mukendi Kabongo+3

Temple University Japan Campus · Universit´e de Kinshasa · Universit´e Protestante au Congo+2

VLM Adaptation Few-Shot Image Classification Few-Shot Learning

Open paper AskPDF arXiv

Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate representations unused. Combining them is not straightforward. Class scores from different representations differ in spread by orders of magnitude for the same query. Direct averaging allocates influence by numerical scale rather than predictive information. We propose Layer-Ensemble Gaussian Discriminant Analysis (LE-GDA), a method that fits regularized shared-covariance discriminants independently to intermediate and final representations extracted in one frozen encoder pass. LE-GDA standardizes each discriminant's class scores per query, selects a small representation multiset on labeled validation data, and combines it with the zero-shot classifier without gradient-based optimization. Across 11 datasets, four CLIP backbones, five shot counts, and three independently sampled K-shot training sets, LE-GDA achieves the highest mean accuracy of all evaluated methods on every backbone, raising the 16-shot mean from 78.01% to 79.54% over a matched GDA-CLIP (final-feature) baseline and improving that baseline for every backbone-shot combination. At one shot, LE-GDA retains a 1.20-point mean gain over the baseline even though covariance estimation is unavailable and per-query standardization is neutral. A control with richer per-class structure inside a single representation does not reproduce the gain, indicating that the benefit comes from combining representations. These results show that intermediate CLIP representations carry information beyond the final embedding and can improve training-free few-shot adaptation. Code and evaluation resources are available at https://github.com/pavodi-NM/le-gda.