Self-Supervised Learning
Also known as SSL
Overview
Self-supervised learning creates training signals from the data itself, for example by matching augmented views, predicting masked content, or using temporal, geometric, and physical consistency. Contrastive learning, masked autoencoders, teacher–student distillation, and joint-embedding predictive architectures are common approaches across images, video, audio, language, medical data, and scientific measurements. These methods can reduce dependence on costly labels and support transfer, but useful representations depend on how well the pretext signal fits the data and downstream task. A central tension is balancing invariance and non-collapse with retaining fine-grained information, while establishing reliable transfer under domain shifts and limited compute remains an open challenge.
Latest papers
280 papers27 papers in the last four weeks, down 13% on the four weeks before. 0.2% of all new papers.
TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Counting
Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning
S3-Tracker: Self-Supervised Surgical Tissue Tracking With Contrastive Random Walks
Self-Supervised Cardiac Phase Detection via Single-Parameter Latent Orbits
"Transforming" LHCb: self-supervised maps of heavy-flavour decays
Effects of model architecture and learning strategies on deep learning-based recognition of activated sludge microscopic images and comparison with quantitative image analysis
Revisiting Spectral Representations in Generative Diffusion Models
Self-Supervised Multi-View 3D Gaze Target Estimation via Probabilistic Ray Marching
DINO Eats Geometry: Self-Supervised Sign Representations that Absorb Articulated Hand Geometry
Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference
An Analysis of Self-supervised Pre-training with Dependent Samples
The microscope is the mask: privileged views and labels from a cryo-ET forward model
Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision
P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning
unsupervised.'' However, different data curation schemes and training objectives embed substantially different human priors on which models rely, and we argue that one unsupervised'' umbrella term is no longer capturing these distinctions. This ambiguity makes it harder to compare unsupervised learning research conducted under different assumptions, coinciding with a sharp decline in papers titled with ``unsupervised'' in flagship computer vision conferences since 2021, despite continued growth of the field. While we fully embrace pre-training as a strong foundation for modern computer vision, we advocate for a community-level effort toward greater conceptual clarity: authors are encouraged to disclose priors in data selection and learning objectives, and to specify which components of a learning pipeline depend on which assumptions. Standardized disclosure practices can improve academic communication, ensure fairer comparisons, and preserve methodological diversity in unsupervised learning.