Hugging Face Trending Papers
Scalable Patch-Level Self-Supervised Learning
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
1d ago
Scalable Patch-Level Self-Supervised Learning
arXiv:2610.10013v1 Announce Type: new Abstract: Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of mul...
arXiv AI
Oct 1
Which Tasks Survive Self-Supervised Learning?
arXiv:2609.38393v1 Announce Type: cross Abstract: Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This p...
Hugging Face Trending Papers
Jul 14
Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?
Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data.
arXiv Computer Vision
Oct 1
Masked Swingers: Harnessing Data Augmentation to Advance Autoencoders for Self-Supervised Learning
arXiv:2609.38278v1 Announce Type: new Abstract: Self-supervised learning (SSL) removes the need for annotations and makes models that are capable across more domains than supervised learning. The aut...
arXiv Machine Learning
Jul 7
Self-Supervised Learning from Structural Invariance
arXiv:2602. 02381v2 Announce Type: replace Abstract: Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related data pairs.
arXiv AI
Sep 24
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
AdaDim introduces a training strategy for self‑supervised learning that adaptively balances dimensionality increase and mutual information reduction. By gradually regularizing the projection head while encouraging feature decorrelation and sample uniformity, AdaDim achieves up to 3% performance gains over standard SSL baselines without relying on costly techniques such as queues or predictor networks. The method demonstrates that optimal SSL models do not simply maximize dimensionality or minimize mutual information, but find a trade‑off between the two.