Papers › Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space

Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space

21 Oct 2022European Conference on Computer Vision 2022 10archive 2025-07-28

Shuo Li, Fang Liu, Zehua Hao, Kaibo Zhao, Licheng Jia

Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classification methods do not need labeled images, because they require tasks to be built on unlabeled images. In order to efficiently build tasks with unlabeled images, we propose a novel single-stage clustering method: Learning Features into Clustering Space (LF2CS), which first set a separable clustering space by fixing the clustering centers and then use a learnable model to learn features into the clustering space. Based on our LF2CS, we put forward an image sampling and c-way k-shot task building method. With this, we propose a novel unsupervised few-shot image classification method, which jointly learns the learnable model, clustering and few-shot image classification. Experiments and visualization show that our LF2CS has a strong ability to generalize to the novel categories. From the perspective of image sampling, we implement four baselines according to how to build tasks. We conduct experiments on the Omniglot, miniImageNet, tieredImageNet and CIFARFS datasets based on the Conv-4 and ResNet-12 backbones. Experimental results show that ours outperform the state-of-the-art methods.

PaperPDFCode

Code

xidianai/LF2CS mentioned in paperpytorchMPL-2.0 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

ClassificationClusteringFew-Shot Image ClassificationImage ClassificationUnsupervised Few-Shot Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) LF2CS Accuracy 53.14 #12 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) LF2CS Accuracy 67.36 #13 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) LF2CS Accuracy 53.16 #6 of 12 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) LF2CS Accuracy 66.59 #6 of 12 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

BASE

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