paper-with-me

Papers

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

2026-06-02 · Julie Mordacq, Vicky Kalogeiton, Steve Oudot arxiv

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. In this work, motivated by connections between neural network generalization and intrinsic dimension (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\mathrm{dim}_\mathrm{MST}$). Across diverse datasets, architectures, and SSL pretraining objectives, we show that IdEst strongly correlates with downstream linear probe performances. Furthermore, we demonstrate that IdEst enables efficient hyperparameter selection, significantly reducing the computational cost compared to supervised alternatives. Our results highlight intrinsic dimensionality as a principled geometric proxy for assessing SSL representations, complementing standard supervised probing protocols.

📄 PDF Abstract BibTeX arXiv:2606.03338

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Meta-Representational Predictive Coding: Biomimetic Self-Supervised Learning

2025-03-22 · Alexander Ororbia, Karl Friston, Rajesh P. N. Rao

Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence. Furthermore, evidence for self-supervised adaptation, such as contrastive formulations, has emerged in recent …

FormSelf-Supervised Learning

Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking

2021-03-17 · Andrew N Carr, Quentin Berthet, Mathieu Blondel, Olivier Teboul 외

Self-supervised pre-training using so-called "pretext" tasks has recently shown impressive performance across a wide range of modalities. In this work, we advance self-supervised learning from permutations, by pre-traini…

ClassificationGeneral ClassificationSelf-Supervised Learning

Object-centric LeJEPA

2026-07-02 · Jakob Geusen, Ender Konukoglu arxiv

Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets. Aligning representations at the level o…

Intrinsically Motivated Self-supervised Learning in Reinforcement Learning

2021-06-26 · Yue Zhao, Chenzhuang Du, Hang Zhao, Tiejun Li

In vision-based reinforcement learning (RL) tasks, it is prevalent to assign auxiliary tasks with a surrogate self-supervised loss so as to obtain more semantic representations and improve sample efficiency. However, abu…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2

On Self-Supervised Image Representations for GAN Evaluation

2021-01-01 · ICLR 2021 1 · Stanislav Morozov, Andrey Voynov, Artem Babenko

The embeddings from CNNs pretrained on Imagenet classification are de-facto standard image representations for assessing GANs via FID, Precision and Recall measures. Despite broad previous criticism of their usage for no…

Contrastive LearningGeneral Classification