5 papers
Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
Gabriel Y. Arteaga, Marius Aasan, Rwiddhi Chakraborty +4
Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This unde…
Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
Thalles Silva, Helio Pedrini, Adín Ramírez Rivera
We present Self-Organizing Visual Prototypes (SOP), a new training technique for unsupervised visual feature learning. Unlike existing prototypical self-supervised learning (SSL) m…
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features
Thalles Silva, Helio Pedrini, Adín Ramírez Rivera
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 pro…
Representation Learning via Consistent Assignment of Views over Random Partitions
Thalles Silva, Adín Ramírez Rivera
We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes…
Self-supervised Learning of Contextualized Local Visual Embeddings
Thalles Santos Silva, Helio Pedrini, Adín Ramírez Rivera
We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks. CLoVE deviate…