# Realistic Evaluation of Transductive Few-Shot Learning

arXiv: https://arxiv.org/abs/2204.11181 · HTML: https://mlsanity.com/paper/2204.11181/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 24 Apr 2022.

## Builds on (most cited first, 30 of 33)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Probabilistic Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.02817/) (2018)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [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)
- [Meta-Learning Probabilistic Inference For Prediction](https://mlsanity.com/paper/1805.09921/) (2018)
- [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)
- [DPGN: Distribution Propagation Graph Network for Few-shot Learning](https://mlsanity.com/paper/2003.14247/) (2020)
- [Leveraging the Feature Distribution in Transfer-based Few-Shot Learning](https://mlsanity.com/paper/2006.03806/) (2020)
- [Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning](https://mlsanity.com/paper/1910.02224/) (2019)
- [Instance Credibility Inference for Few-Shot Learning](https://mlsanity.com/paper/2003.11853/) (2020)
- [TaskNorm: Rethinking Batch Normalization for Meta-Learning](https://mlsanity.com/paper/2003.03284/) (2020)
- [Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks](https://mlsanity.com/paper/1905.12917/) (2019)
- [Empirical Bayes Transductive Meta-Learning with Synthetic Gradients](https://mlsanity.com/paper/2004.12696/) (2020)
- [Transductive Information Maximization For Few-Shot Learning](https://mlsanity.com/paper/2008.11297/) (2020)
- [An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning](https://mlsanity.com/paper/1904.08479/) (2019)
- [Learning to Stop While Learning to Predict](https://mlsanity.com/paper/2006.05082/) (2020)

## Built on by (most cited first, 27 of 27)

- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [Boosting Vision-Language Models with Transduction](https://mlsanity.com/paper/2406.01837/) (2024)
- [Transductive Zero-Shot and Few-Shot CLIP](https://mlsanity.com/paper/2405.18437/) (2024)
- [Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement](https://mlsanity.com/paper/2304.11598/) (2023)
- [A Strong Baseline for Generalized Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2211.14126/) (2022)
- [Conformal Prediction for Zero-Shot Models](https://mlsanity.com/paper/2505.24693/) (2025)
- [Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings](https://mlsanity.com/paper/2303.09352/) (2023)
- [Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification](https://mlsanity.com/paper/2209.08527/) (2022)
- [Open-Set Likelihood Maximization for Few-Shot Learning](https://mlsanity.com/paper/2301.08390/) (2023)
- [Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference](https://mlsanity.com/paper/2210.14545/) (2022)
- [Prototypes-oriented Transductive Few-shot Learning with Conditional Transport](https://mlsanity.com/paper/2308.03047/) (2023)
- [Adaptive manifold for imbalanced transductive few-shot learning](https://mlsanity.com/paper/2304.14281/) (2023)
- [A transductive few-shot learning approach for classification of digital histopathological slides from liver cancer](https://mlsanity.com/paper/2311.17740/) (2023)
- [What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective](https://mlsanity.com/paper/2606.14299/) (2026)
- [Model-Agnostic Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2206.09236/) (2022)
- [Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings](https://mlsanity.com/paper/2209.11481/) (2022)
- [UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning](https://mlsanity.com/paper/2412.16739/) (2024)
- [A Maximum Log-Likelihood Method for Imbalanced Few-Shot Learning Tasks](https://mlsanity.com/paper/2211.14668/) (2022)
- [Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagation](https://mlsanity.com/paper/2311.17096/) (2023)
- [Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need](https://mlsanity.com/paper/2503.22193/) (2025)
- [Object-Centric Cropping for Visual Few-Shot Classification](https://mlsanity.com/paper/2508.00218/) (2025)
- [Information Maximization for Long-Tailed Semi-Supervised Domain Generalization](https://mlsanity.com/paper/2603.08434/) (2026)
- [DirPA: Addressing Prior Shift in Imbalanced Few-shot Crop-type Classification](https://mlsanity.com/paper/2603.12905/) (2026)
- [PhenoStitch: Training-Free Panoptic Crop Mapping from Satellite Image Time Series](https://mlsanity.com/paper/2608.00870/) (2026)
- [Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification](https://mlsanity.com/paper/2609.23758/) (2026)
- [Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images](https://mlsanity.com/paper/2609.31040/) (2026)
- [RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces](https://mlsanity.com/paper/2610.05852/) (2026)

## Abstract (arXiv)

Transductive inference is widely used in few-shot learning, as it leverages the statistics of the unlabeled query set of a few-shot task, typically yielding substantially better performances than its inductive counterpart. The current few-shot benchmarks use perfectly class-balanced tasks at inference. We argue that such an artificial regularity is unrealistic, as it assumes that the marginal label probability of the testing samples is known and fixed to the uniform distribution. In fact, in realistic scenarios, the unlabeled query sets come with arbitrary and unknown label marginals. We introduce and study the effect of arbitrary class distributions within the query sets of few-shot tasks at inference, removing the class-balance artefact. Specifically, we model the marginal probabilities of the classes as Dirichlet-distributed random variables, which yields a principled and realistic sampling within the simplex. This leverages the current few-shot benchmarks, building testing tasks with arbitrary class distributions. We evaluate experimentally state-of-the-art transductive methods over 3 widely used data sets, and observe, surprisingly, substantial performance drops, even below inductive methods in some cases. Furthermore, we propose a generalization of the mutual-information loss, based on α-divergences, which can handle effectively class-distribution variations. Empirically, we show that our transductive α-divergence optimization outperforms state-of-the-art methods across several data sets, models and few-shot settings. Our code is publicly available at https://github.com/oveilleux/RealisticTransductiveFewShot.