Self-Organizing Visual Prototypes for Non-Parametric Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Silva, Thalles, Pedrini, Helio, Rivera, Adín Ramírez
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912398792720384
author Silva, Thalles
Pedrini, Helio
Rivera, Adín Ramírez
author_facet Silva, Thalles
Pedrini, Helio
Rivera, Adín Ramírez
contents 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 SOP strategy. In this strategy, a prototype is represented by many semantically similar representations, or support embeddings (SEs), each containing a complementary set of features that together better characterize their region in space and maximize training performance. We reaffirm the feasibility of non-parametric SSL by introducing novel non-parametric adaptations of two loss functions that implement the SOP strategy. Notably, we introduce the SOP Masked Image Modeling (SOP-MIM) task, where masked representations are reconstructed from the perspective of multiple non-parametric local SEs. We comprehensively evaluate the representations learned using the SOP strategy on a range of benchmarks, including retrieval, linear evaluation, fine-tuning, and object detection. Our pre-trained encoders achieve state-of-the-art performance on many retrieval benchmarks and demonstrate increasing performance gains with more complex encoders.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21533
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
Silva, Thalles
Pedrini, Helio
Rivera, Adín Ramírez
Computer Vision and Pattern Recognition
Machine Learning
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 SOP strategy. In this strategy, a prototype is represented by many semantically similar representations, or support embeddings (SEs), each containing a complementary set of features that together better characterize their region in space and maximize training performance. We reaffirm the feasibility of non-parametric SSL by introducing novel non-parametric adaptations of two loss functions that implement the SOP strategy. Notably, we introduce the SOP Masked Image Modeling (SOP-MIM) task, where masked representations are reconstructed from the perspective of multiple non-parametric local SEs. We comprehensively evaluate the representations learned using the SOP strategy on a range of benchmarks, including retrieval, linear evaluation, fine-tuning, and object detection. Our pre-trained encoders achieve state-of-the-art performance on many retrieval benchmarks and demonstrate increasing performance gains with more complex encoders.
title Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.21533