@rbalestr.bsky.social
Pinned
Understanding the evolution of historical maps is key to track the development of civilizations (urbanization, environmental changes, ...). We show how to use Self Supervised Learning to do that without supervision!
arxiv.org/abs/2411.17425
(SSL workshop NeurIPS24)
arxiv.org/abs/2411.17425
(SSL workshop NeurIPS24)
Want to use SOTA Self Supervised Learning (SSL) methods on noisy data? We provide a novel training curriculum that significantly improves test performance on clean and noisy samples! The approach is fully SSL and works on any method (DINOv2, MoCo, ...)
arxiv.org/abs/2505.12191
arxiv.org/abs/2505.12191
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a...
arxiv.org
May 20, 2025 at 2:38 PM
Want to use SOTA Self Supervised Learning (SSL) methods on noisy data? We provide a novel training curriculum that significantly improves test performance on clean and noisy samples! The approach is fully SSL and works on any method (DINOv2, MoCo, ...)
arxiv.org/abs/2505.12191
arxiv.org/abs/2505.12191
Want better training and geometric insights for Sparse AutoEncoders (SAEs)? Search no more... We leverage spline theory to provide a new "EM-like" training algo (PAM-SGD) and to delve into SAE geometry with connections to PCA, k-means, and more...
arxiv.org/abs/2505.11836
arxiv.org/abs/2505.11836
May 20, 2025 at 2:08 PM
Want better training and geometric insights for Sparse AutoEncoders (SAEs)? Search no more... We leverage spline theory to provide a new "EM-like" training algo (PAM-SGD) and to delve into SAE geometry with connections to PCA, k-means, and more...
arxiv.org/abs/2505.11836
arxiv.org/abs/2505.11836
Learning by reconstruction captures uninformative details in your data. This “attention to details” biases the ViT’s attention. Our solution: a new token aggregator->improves (significantly) MAE linear probe perf. and (slightly) JEPAs like I-JEPA
arxiv.org/abs/2412.03215
arxiv.org/abs/2412.03215
December 5, 2024 at 6:47 PM
Learning by reconstruction captures uninformative details in your data. This “attention to details” biases the ViT’s attention. Our solution: a new token aggregator->improves (significantly) MAE linear probe perf. and (slightly) JEPAs like I-JEPA
arxiv.org/abs/2412.03215
arxiv.org/abs/2412.03215
Understanding the evolution of historical maps is key to track the development of civilizations (urbanization, environmental changes, ...). We show how to use Self Supervised Learning to do that without supervision!
arxiv.org/abs/2411.17425
(SSL workshop NeurIPS24)
arxiv.org/abs/2411.17425
(SSL workshop NeurIPS24)
December 2, 2024 at 2:22 PM
Understanding the evolution of historical maps is key to track the development of civilizations (urbanization, environmental changes, ...). We show how to use Self Supervised Learning to do that without supervision!
arxiv.org/abs/2411.17425
(SSL workshop NeurIPS24)
arxiv.org/abs/2411.17425
(SSL workshop NeurIPS24)