# Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference

arXiv: https://arxiv.org/abs/2210.14545 · HTML: https://mlsanity.com/paper/2210.14545/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [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)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (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)
- [Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?](https://mlsanity.com/paper/2012.06166/) (2020)
- [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)
- [Leveraging the Feature Distribution in Transfer-based Few-Shot Learning](https://mlsanity.com/paper/2006.03806/) (2020)
- [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)
- [Transductive Information Maximization For Few-Shot Learning](https://mlsanity.com/paper/2008.11297/) (2020)
- [Iterative label cleaning for transductive and semi-supervised few-shot learning](https://mlsanity.com/paper/2012.07962/) (2020)
- [Few-Shot Learning with Localization in Realistic Settings](https://mlsanity.com/paper/1904.08502/) (2019)
- [TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification](https://mlsanity.com/paper/2003.06670/) (2020)
- [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)
- [Transductive Few-Shot Classification on the Oblique Manifold](https://mlsanity.com/paper/2108.04009/) (2021)
- [An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering](https://mlsanity.com/paper/1302.1552/) (2013)
- [Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift](https://mlsanity.com/paper/2105.11804/) (2021)
- [Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions](https://mlsanity.com/paper/1505.00218/) (2015)

## Built on by (most cited first, 9 of 9)

- [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)
- [Realistic Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.03729/) (2025)
- [Open-Set Likelihood Maximization for Few-Shot Learning](https://mlsanity.com/paper/2301.08390/) (2023)
- [A transductive few-shot learning approach for classification of digital histopathological slides from liver cancer](https://mlsanity.com/paper/2311.17740/) (2023)
- [SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification](https://mlsanity.com/paper/2605.13672/) (2026)
- [Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning](https://mlsanity.com/paper/2404.04983/) (2024)
- [UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning](https://mlsanity.com/paper/2412.16739/) (2024)
- [Aggregated f-average Neural Network applied to Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2310.05566/) (2023)

## Abstract (arXiv)

Standard few-shot benchmarks are often built upon simplifying assumptions on the query sets, which may not always hold in practice. In particular, for each task at testing time, the classes effectively present in the unlabeled query set are known a priori, and correspond exactly to the set of classes represented in the labeled support set. We relax these assumptions and extend current benchmarks, so that the query-set classes of a given task are unknown, but just belong to a much larger set of possible classes. Our setting could be viewed as an instance of the challenging yet practical problem of extremely imbalanced K-way classification, K being much larger than the values typically used in standard benchmarks, and with potentially irrelevant supervision from the support set. Expectedly, our setting incurs drops in the performances of state-of-the-art methods. Motivated by these observations, we introduce a PrimAl Dual Minimum Description LEngth (PADDLE) formulation, which balances data-fitting accuracy and model complexity for a given few-shot task, under supervision constraints from the support set. Our constrained MDL-like objective promotes competition among a large set of possible classes, preserving only effective classes that befit better the data of a few-shot task. It is hyperparameter free, and could be applied on top of any base-class training. Furthermore, we derive a fast block coordinate descent algorithm for optimizing our objective, with convergence guarantee, and a linear computational complexity at each iteration. Comprehensive experiments over the standard few-shot datasets and the more realistic and challenging i-Nat dataset show highly competitive performances of our method, more so when the numbers of possible classes in the tasks increase. Our code is publicly available at https://github.com/SegoleneMartin/PADDLE.