Zero-Shot Image Classification

Ask about this topic

Overview

Zero-shot image classification studies how to recognize classes with no labeled training images, usually by connecting visual features to class names, attributes, or other semantic descriptions. A common approach uses pretrained vision-language models such as CLIP to compare image and text embeddings; other methods use semantic prototypes, generated features, or generative models. Researchers also improve predictions through prompt design, similarity calibration, region-level evidence, and adaptation using unlabeled target images, including in specialized domains such as medicine and remote sensing. A central tension is that richer prompts and target-specific adaptation can help, but performance remains sensitive to wording, distribution shifts, and spurious visual cues—and using target data can blur the boundary between zero-shot recognition and adaptation.

Latest papers

CardsList

49 papers4 papers in the last four weeks, down 43% on the four weeks before. 0.0% of all new papers.

  1. Zero-Shot Multi-Class Wafer Map Classification with Rule-Ordered Prompts for Large Multimodal Models

    Oct 26, 2026Tianjian Cao, Jun TaoSemiconductor ManufacturingImage Classification

    Fudan University Shanghai, China

  2. SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis

    Oct 15, 2026Ting Liu, Haoran Lai, HaobinChen +2Radiology VLMsContrastive Learning

    School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230026, P.R. China · Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, 215123, P.R. China

  3. MicroCLIP: Connecting Text and Microscopy Images via Contrastive Language--Image Pretraining

    Oct 13, 2026Yanran Ruan, Zhixiang Wei, Shiyao Hong +5Fluorescence MicroscopyMicroscopy Image Analysis

    University of Science and Technology of China

  4. Benchmarking CLIP for Zero-Shot Face and Periocular Gender Estimation

    Oct 5, 2026Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades +1Zero-Shot Image Classification

    School of Information Technology, Halmstad University, Sweden · Computer Graphics and Vision and AI Group, University of Balearic Islands, Spain

  5. LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder

    Oct 2, 2026Anh-Khoa Dinh-Duc, Duc-Tai Dinh, Tam V. Nguyen +1Referring Expression ComprehensionVLM Adaptation

    University of Science, Ho Chi Minh City, Vietnam · Viet Nam National University, Ho Chi Minh City, Vietnam · University of Dayton, USA

  6. A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations

    Sep 27, 2026Yoav Evron, Michal Bar-Asher Siegal, Michael FireVLM EvaluationHistorical Document Analysis

    Faculty of Computer and Information Science, Ben-Gurion University of the Negev, Be’er Sheva, Israel · The Goldstein-Goren Department of Jewish Thought, Ben-Gurion University of the Negev, Be’er Sheva, Israel

  7. Refining Cytology Predictions with Conditional Random Fields

    Sep 25, 2026Manon Dausort, Tiffanie Godelaine, Karim El Khoury +3Medical Image ClassificationConditional Random Fields

    ICTEAM, Universit´e Catholique de Louvain, Belgium

  8. From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning

    Sep 14, 2026Weize Li, Zhicheng Zhao, Fei SuZero-Shot LearningVLM Reasoning

    Beijing University of Posts and Telecommunications · Beijing Key Laboratory of Network System and Network Culture · Key Laboratory of Interactive Technology and Experience System

  9. GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification

    Sep 11, 2026Wei-Yang Alex Lee, Rudrasis Chakraborty, Vishnu LokhandeZero-Shot Image ClassificationOptimal Transport

    SUNY Buffalo · Lawrence Livermore National Lab

  10. Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance

    Sep 4, 2026Samir Char, Carles Domingo-Enrich, Randall BalestrieroVision-Language ModelsVision-Language Pretraining

    Microsoft · Brown University

  11. IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition

    Sep 3, 2026Nazim-E-Alam, Tarek Rahman, Md Kishor MorolVLM RobustnessPrompt Sensitivity

    American International University Bangladesh · United International University · ELITE Research Lab, Queens, New York, USA

  12. When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP

    Sep 1, 2026Shota Sato, Hajime Kiyama, Tosho Hirasawa +1Cross-Modal AlignmentZero-Shot Image Classification

    Hitotsubashi University

  13. GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models

    Aug 29, 2026Pedram MohajerAnsari, Amir Salarpour, Run Wang +1Test-Time Adaptation of VLMsVLM Robustness

    Clemson University Clemson, SC, USA

  14. G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification

    Aug 27, 2026Zehua Hao, Fang Liu, Qinliang Wang +3Zero-Shot Image ClassificationVLM Inference

    Xidian University Xi’an, Shaanxi, China

  15. From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model

    Aug 18, 2026Qi Yu, Zhichen Zeng, Katherine Tieu +8VLM AdaptationTest-Time Adaptation of VLMs

    University of Illinois Urbana-Champaign · Amazon · Wayne State University

  16. CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension

    Aug 13, 2026William Heyden, Habib Ullah, Muhammad Salman Siddiqui +1Zero-Shot LearningZero-Shot Image Classification

    Faculty of Science and Technology (REALTEK) Norwegian University of Life Sciences NMBU 1430 Ås, Norway

  17. Visual Distribution Anchoring for Efficient Prompt Tuning

    Jul 31, 2026Pouya Parsa, Raoof Zare Moayedi, Seongjin ChoiSource-Free Domain AdaptationDomain Adaptation

    University of Minnesota USA

  18. Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models

    Jul 21, 2026Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin +3Vision-Language ModelsDistribution Shift

    Carnegie Mellon University, USA

  19. MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration

    Jul 13, 2026Zheng Zeng, Deepak Sridhar, Nuno VasconcelosVLM RobustnessVLM Adaptation

    University of California, San Diego, USA

  20. How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation

    Jul 4, 2026Saba Fathi, Fardin Ayar, Maryam Abdolali +3ClassificationZero-Shot Image Classification

    2Amirkabir University of Technology, Tehran, Iran · 1K. N. Toosi University of Technology, Tehran, Iran · 3The University of Tokyo, Tokyo, Japan

  21. Self-Improving Diffusion Classifiers with Minority Preference Optimization

    Jul 4, 2026Hyunsoo Kim, Jungmyung Wi, Soobin Um +2Diffusion Model AlignmentLong-Tailed Classification

    1Korea University · 2Kook Min University · 3Kyung Hee University

  22. CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning

    Jul 1, 2026Can Wang, Jiangnan Li, Mingyu Li +4Zero-Shot LearningZero-Shot Image Classification

    School of Computer Science and Technology, Qingdao University, Qingdao, China · School of Software Engineering, Tongji University, Shanghai, China

  23. Physiology-Aware CNN and Zero-Shot Multimodal LLMs for ECG Image Classification: A Comparative Study

    Jun 22, 2026Khalil Ahammad, Derek Abbott, Mohsen DorrakiElectrocardiographyMultimodal Large Language Models

    School of Computer Science and Information Technology, Adelaide University, SA 5005, Australia · Australian Institute for Machine Learning (AIML), Adelaide, Australia · Pi MedTech, Adelaide, Australia +1

  24. Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification

    Jun 20, 2026Zhiyuan Tao, Srikumar Sastry, Matthew J Thompson +9Hierarchical ClassificationContrastive Learning

    The Ohio State University · Washington University in St. Louis · Neuromatch +1

  25. Multimodal Concept Bottleneck Models

    Jun 18, 2026Tongqing Shi, Ge Yan, Tuomas Oikarinen +1Concept Bottleneck ModelsVLM Interpretability

    UC San Diego

  26. Beyond Templates: Revisiting Zero-Shot Remote Sensing through Meta-Prompting

    Jun 15, 2026Eirini Baltzi, Dionysis Christopoulos, Sotiris Spanos +2Remote Sensing Image UnderstandingZero-Shot Image Classification

    Remote Sensing Lab, National Technical University of Athens Athens, Greece · Department of Engineering and Sciences, Universitas Mercatorum Rome, Italy

  27. Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)

    Jun 13, 2026Pengxiao Han, Changkun Ye, Yanshuo Wang +5Source-Free Domain AdaptationZero-Shot Learning

    Australian National University, Canberra, ACT, Australia · China North Vehicle Research Institute, Beijing, China · The Hong Kong Polytechnic University, Hong Kong SAR, China +3

  28. Multi-Label Test-Time Adaptation with Bayesian Conditional Priors

    Jun 11, 2026Qiru Li, Ao Zhou, Zhiwei Jiang +4Multi-Label ClassificationTest-Time Adaptation

    State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China

  29. Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels

    Jun 10, 2026Cheng Chen, Jingyu Zhou, Yifan Zhao +1Multi-Label ClassificationVLM Adaptation

    State Key Laboratory of Virtual Reality Technology and Systems, SCSE & QRI, Beihang University, Beijing 100191, China.

  30. Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

    Jun 1, 2026Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1VLM RobustnessVision-Language Models

    School of Computing and Information Systems, The University of Melbourne, Victoria, Australia.