Papers › UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning

UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning

21 Dec 2024CVPR 2025 1arXiv:2412.16739archive 2025-07-28

Long Zhou, Fereshteh Shakeri, Aymen Sadraoui, Mounir Kaaniche, Jean-Christophe Pesquet, Ismail Ben Ayed

Transductive few-shot learning has recently triggered wide attention in computer vision. Yet, current methods introduce key hyper-parameters, which control the prediction statistics of the test batches, such as the level of class balance, affecting performances significantly. Such hyper-parameters are empirically grid-searched over validation data, and their configurations may vary substantially with the target dataset and pre-training model, making such empirical searches both sub-optimal and computationally intractable. In this work, we advocate and introduce the unrolling paradigm, also referred to as "learning to optimize", in the context of few-shot learning, thereby learning efficiently and effectively a set of optimized hyper-parameters. Specifically, we unroll a generalization of the ubiquitous Expectation-Maximization (EM) optimizer into a neural network architecture, mapping each of its iterates to a layer and learning a set of key hyper-parameters over validation data. Our unrolling approach covers various statistical feature distributions and pre-training paradigms, including recent foundational vision-language models and standard vision-only classifiers. We report comprehensive experiments, which cover a breadth of fine-grained downstream image classification tasks, showing significant gains brought by the proposed unrolled EM algorithm over iterative variants. The achieved improvements reach up to 10% and 7.5% on vision-only and vision-language benchmarks, respectively.

PaperPDFConference PDFCode

Code

zhoulong0/unem-transductive officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot LearningFew-Shot Learning - 4 shotsImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Learning Mini-ImageNet - 10-Shot Learning UNEM-Gaussian Accuracy 65.7 #1 of 1 Archive leaderboard report
Few-Shot Learning Mini-ImageNet - 20-Shot Learning UNEM-Gaussian Accuracy 73.2 #1 of 1 Archive leaderboard report
Few-Shot Learning Mini-ImageNet - 5-Shot Learning UNEM-Gaussian Accuracy 66.4% #3 of 3 Archive leaderboard report
Few-Shot Learning tieredImageNet - 5-shot UNEM-Gaussian Accuracy 52.3 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionSETSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections