mlsanityData to 14 Oct 2026

Transductive Zero-Shot and Few-Shot CLIP

arXiv 2405.18437 ↗First posted 8 Apr 2024cs.CV cs.AIcited by 32

Not on the map. Why?

Abstract (arXiv)

Transductive inference has been widely investigated in few-shot image classification, but completely overlooked in the recent, fast growing literature on adapting vision-langage models like CLIP. This paper addresses the transductive zero-shot and few-shot CLIP classification challenge, in which inference is performed jointly across a mini-batch of unlabeled query samples, rather than treating each instance independently. We initially construct informative vision-text probability features, leading to a classification problem on the unit simplex set. Inspired by Expectation-Maximization (EM), our optimization-based classification objective models the data probability distribution for each class using a Dirichlet law. The minimization problem is then tackled with a novel block Majorization-Minimization algorithm, which simultaneously estimates the distribution parameters and class assignments. Extensive numerical experiments on 11 datasets underscore the benefits and efficacy of our batch inference approach.On zero-shot tasks with test batches of 75 samples, our approach yields near 20% improvement in ImageNet accuracy over CLIP's zero-shot performance. Additionally, we outperform state-of-the-art methods in the few-shot setting. The code is available at: https://github.com/SegoleneMartin/transductive-CLIP.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 34 of its 59 references that are in the map. First posted on arXiv 8 Apr 2024.

Builds on

34 of 59 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2013Describing Textures in the Wildcited by 2,125
  7. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  8. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  9. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  10. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  11. 2019A Closer Look at Few-shot Classificationcited by 684
  12. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 570
22 more
  1. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  2. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  3. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  4. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  5. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  6. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  7. 2019Prototype Rectification for Few-Shot Learningcited by 97
  8. 2020Laplacian Regularized Few-Shot Learningcited by 92
  9. 2022PLOT: Prompt Learning with Optimal Transport for Vision-Language Modelscited by 64
  10. 2017von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verificationcited by 46
  11. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  12. 2020Iterative label cleaning for transductive and semi-supervised few-shot learningcited by 40
  13. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  14. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 27
  15. 2018Deep Neural Network Structures Solving Variational Inequalitiescited by 26
  16. 2013An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clusteringcited by 17
  17. 2023Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddingscited by 11
  18. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  19. 2022Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inferencecited by 9
  20. 2023Prototypes-oriented Transductive Few-shot Learning with Conditional Transportcited by 8
  21. 2015Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutionscited by 7
  22. 2022Mixture of von Mises-Fisher distribution with sparse prototypescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 15; 2026: 11.

32 papers.

Sort:

By area:

  1. 2024Boosting Vision-Language Models with Transductioncited by 36
  2. 2025Conformal Prediction for Zero-Shot Modelscited by 15
  3. 2025Realistic Test-Time Adaptation of Vision-Language Modelscited by 14
  4. 2024textttBATCLIP: Bimodal Online Test-Time Adaptation for CLIPcited by 11
  5. 2025Logits DeConfusion with CLIP for Few-Shot Learningcited by 11
  6. 2024Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classificationcited by 8
  7. 2024Boosting Vision-Language Models for Histopathology Classification: Predict all at oncecited by 8
  8. 2025Online Gaussian Test-Time Adaptation of Vision-Language Modelscited by 7
  9. 2025RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigmcited by 7
  10. 2025Slicing the Gaussian Mixture Wasserstein Distancecited by 7
  11. 2024LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Textscited by 3
  12. 2025Generate, Transduct, Adapt: Iterative Transduction with VLMscited by 2
20 more
  1. 2025Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learningcited by 2
  2. 2025Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognitioncited by 2
  3. 2026ZAYA1-VL-8B Technical Reportcited by 2
  4. 2026Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocolscited by 2
  5. 2024UNEM: UNrolled Generalized EM for Transductive Few-Shot Learningcited by 1
  6. 2025Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidancecited by 1
  7. 2025Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classificationcited by 1
  8. 2025GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrievalcited by 1
  9. 2026Leveraging Prediction Entropy for Automatic Prompt Weighting in Zero-Shot Audio-Language Classificationcited by 1
  10. 2026Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learningcited by 1
  11. 2026ORION: ORthonormal Text Encoding for Universal VLM AdaptatIONcited by 1
  12. 2025Dynamic Relation Inference via Verb Embeddingscited by 0
  13. 2025Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representationscited by 0
  14. 2025Language-Aware Information Maximization for Transductive Few-Shot CLIPcited by 0
  15. 2026ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarioscited by 0
  16. 2026Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognitioncited by 0
  17. 2026One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensemblingcited by 0
  18. 2026BIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensorscited by 0
  19. 2026Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Modelcited by 0
  20. 2026From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrievalcited by 0