← Search

Helio Pedrini

2 accepted papers

2025

Self-Organizing Visual Prototypes for Non-Parametric Representation Learning

ICML 2025poster

We present Self-Organizing Visual Prototypes (SOP), a new training technique for unsupervised visual feature learning. Unlike existing prototypical self-supervised learning (SSL) methods that rely on a single prototype to encode all relevant features of a hidden cluster in the data, we propose the S…

Cited by 0SourcePDFScholar
2024

Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features

ICML 2024poster

This paper introduces a novel approach to improving the training stability of self-supervised learning (SSL) methods by leveraging a non-parametric memory of seen concepts. The proposed method involves augmenting a neural network with a memory component to stochastically compare current image views…