# Transductive Zero-Shot and Few-Shot CLIP

arXiv: https://arxiv.org/abs/2405.18437 · HTML: https://mlsanity.com/paper/2405.18437/

## 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 (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Prototype Rectification for Few-Shot Learning](https://mlsanity.com/paper/1911.10713/) (2019)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [PLOT: Prompt Learning with Optimal Transport for Vision-Language Models](https://mlsanity.com/paper/2210.01253/) (2022)
- [von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification](https://mlsanity.com/paper/1706.04264/) (2017)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Iterative label cleaning for transductive and semi-supervised few-shot learning](https://mlsanity.com/paper/2012.07962/) (2020)
- [Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement](https://mlsanity.com/paper/2304.11598/) (2023)
- [Realistic Evaluation of Transductive Few-Shot Learning](https://mlsanity.com/paper/2204.11181/) (2022)
- [Deep Neural Network Structures Solving Variational Inequalities](https://mlsanity.com/paper/1808.07526/) (2018)
- [An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering](https://mlsanity.com/paper/1302.1552/) (2013)
- [Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings](https://mlsanity.com/paper/2303.09352/) (2023)
- [Open-Set Likelihood Maximization for Few-Shot Learning](https://mlsanity.com/paper/2301.08390/) (2023)

## Built on by (most cited first, 30 of 32)

- [Boosting Vision-Language Models with Transduction](https://mlsanity.com/paper/2406.01837/) (2024)
- [Conformal Prediction for Zero-Shot Models](https://mlsanity.com/paper/2505.24693/) (2025)
- [Realistic Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.03729/) (2025)
- [textttBATCLIP: Bimodal Online Test-Time Adaptation for CLIP](https://mlsanity.com/paper/2412.02837/) (2024)
- [Logits DeConfusion with CLIP for Few-Shot Learning](https://mlsanity.com/paper/2504.12104/) (2025)
- [Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification](https://mlsanity.com/paper/2409.00698/) (2024)
- [Boosting Vision-Language Models for Histopathology Classification: Predict all at once](https://mlsanity.com/paper/2409.01883/) (2024)
- [Online Gaussian Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.04352/) (2025)
- [RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm](https://mlsanity.com/paper/2502.12513/) (2025)
- [Slicing the Gaussian Mixture Wasserstein Distance](https://mlsanity.com/paper/2504.08544/) (2025)
- [LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts](https://mlsanity.com/paper/2410.08211/) (2024)
- [Generate, Transduct, Adapt: Iterative Transduction with VLMs](https://mlsanity.com/paper/2501.06031/) (2025)
- [Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning](https://mlsanity.com/paper/2508.03102/) (2025)
- [Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition](https://mlsanity.com/paper/2510.26466/) (2025)
- [ZAYA1-VL-8B Technical Report](https://mlsanity.com/paper/2605.08560/) (2026)
- [Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols](https://mlsanity.com/paper/2608.30420/) (2026)
- [UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning](https://mlsanity.com/paper/2412.16739/) (2024)
- [Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance](https://mlsanity.com/paper/2503.15886/) (2025)
- [Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification](https://mlsanity.com/paper/2503.24017/) (2025)
- [GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval](https://mlsanity.com/paper/2509.23370/) (2025)
- [Leveraging Prediction Entropy for Automatic Prompt Weighting in Zero-Shot Audio-Language Classification](https://mlsanity.com/paper/2601.05011/) (2026)
- [Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning](https://mlsanity.com/paper/2602.18867/) (2026)
- [ORION: ORthonormal Text Encoding for Universal VLM AdaptatION](https://mlsanity.com/paper/2602.19530/) (2026)
- [Dynamic Relation Inference via Verb Embeddings](https://mlsanity.com/paper/2503.13021/) (2025)
- [Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations](https://mlsanity.com/paper/2508.21769/) (2025)
- [Language-Aware Information Maximization for Transductive Few-Shot CLIP](https://mlsanity.com/paper/2509.00305/) (2025)
- [ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios](https://mlsanity.com/paper/2601.03011/) (2026)
- [Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition](https://mlsanity.com/paper/2603.07911/) (2026)
- [One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling](https://mlsanity.com/paper/2606.08126/) (2026)
- [BIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensors](https://mlsanity.com/paper/2609.08673/) (2026)

## 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.