Zero-Shot Image Classification

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

50 papers2 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

  1. Behavioral Affinity Transduction for Zero-Shot Vision-Language Classification

    Nov 2, 2026Junxi Huang, Wenshuo Chen, Xiucheng Wang +5Zero-Shot Image ClassificationTransductive Learning

  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

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

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

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

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

  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

  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

  7. Refining Cytology Predictions with Conditional Random Fields

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

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

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

  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

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

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

  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

  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

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

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

  14. 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

  15. 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

  16. Visual Distribution Anchoring for Efficient Prompt Tuning

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

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

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

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

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

  19. Self-Improving Diffusion Classifiers with Minority Preference Optimization

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

  20. 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

  21. 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

  22. 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

  23. Multimodal Concept Bottleneck Models

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

  24. 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

  25. 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

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

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

  27. 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