Masked Autoencoders Are Scalable Vision Learners
Fast representation learning with autoencoders by masked image reconstruction
#self-supervised
#image-representation
InfoGCL: Information-Aware Graph Contrastive Learning
Benchmarking graph contrastive learning methods by dissecting them
#graph-neural-network
#self-supervised
#graph-representation
Hybrid Generative-Contrastive Representation Learning
Image representation learning in both generative-contrastive way
#self-supervised
#computer-vision
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
Learning musical representation of symbolic music scores
#music-representation
#self-supervised
Anticipative Video Transformer
Action anticipation from video with transformers
#vision-transformer
#self-supervised
#video-understanding
Towards Unified Surgical Skill Assessment
"Beep. Your surgical skill scored 9 out of 100, Dr. Kim"
#medical-imaging
#self-supervised
Self-Supervised Learning with Swin Transformers
Swin-T + (MoCo + BYOL) = Encouraging result
#vision-transformer
#computer-vision
#self-supervised
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
SimCLR, MoCo, BYOL, and SwAV through time!
#video-understanding
#self-supervised
Clean Images are Hard to Reblur: A New Clue for Deblurring
Clean images are hard to reblur, so make your image difficult to reblur.
#image-processing
#self-supervised
#deblurring
Model-Contrastive Federated Learning
Local model representations are contrastively-encouraged to follow the global representation during federated learning
#federated-learning
#self-supervised
Knowledge-aware Contrastive Molecular Graph Learning
Molecular graph representation learning with hard-coded domain knowledge
#graph-representation
#self-supervised
#molecular-graph
Self-Supervised Adaptation for Video Super-Resolution
Video super-resolution algorithms are further enhanced by self-supervised learning
#self-supervised
#super-resolution
#video-processing