Score: 1

Unsupervised Image Classification with Adaptive Nearest Neighbor Selection and Cluster Ensembles

Published: November 20, 2025 | arXiv ID: 2511.16213v1

By: Melih Baydar, Emre Akbas

Potential Business Impact:

Groups pictures automatically, making computers smarter.

Business Areas:
Image Recognition Data and Analytics, Software

Unsupervised image classification, or image clustering, aims to group unlabeled images into semantically meaningful categories. Early methods integrated representation learning and clustering within an iterative framework. However, the rise of foundational models have recently shifted focus solely to clustering, bypassing the representation learning step. In this work, we build upon a recent multi-head clustering approach by introducing adaptive nearest neighbor selection and cluster ensembling strategies to improve clustering performance. Our method, "Image Clustering through Cluster Ensembles" (ICCE), begins with a clustering stage, where we train multiple clustering heads on a frozen backbone, producing diverse image clusterings. We then employ a cluster ensembling technique to consolidate these potentially conflicting results into a unified consensus clustering. Finally, we train an image classifier using the consensus clustering result as pseudo-labels. ICCE achieves state-of-the-art performance on ten image classification benchmarks, achieving 99.3% accuracy on CIFAR10, 89% on CIFAR100, and 70.4% on ImageNet datasets, narrowing the performance gap with supervised methods. To the best of our knowledge, ICCE is the first fully unsupervised image classification method to exceed 70% accuracy on ImageNet.

Country of Origin
🇹🇷 Turkey

Page Count
19 pages

Category
Computer Science:
CV and Pattern Recognition