arXiv AI By Scott C. Lowe, Joakim Bruslund Haurum, Sageev Oore, Thomas B. Moeslund, Graham W. Taylor

An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders

Read the original on arXiv AI →

The paper investigates whether pretrained image models can generalize to unseen datasets by clustering their embeddings. Using encoders trained only on ImageNet‑1k, both supervised and self‑supervised, the authors evaluate clustering performance on out‑of‑domain images. They find that supervised encoders perform better within the training domain, while self‑supervised encoders excel far outside it, and that fine‑tuning self‑supervised models reverses this trend. Additionally, the study shows that the silhouette score in UMAP‑reduced space correlates strongly with clustering accuracy, offering a proxy metric when labels are unavailable.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Jul 9

Converge to Surprise: Evolutionary Self-supervised Image Clustering

arXiv:2607. 06887v1 Announce Type: new Abstract: Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive split, a masked patch or entity, an EMA-teacher output, a pseudo-label, or a differentiable information-theoretic functional.

By Canlin Zhang, Xiuwen Liu