Self Supervised Learning

Self-supervised learning (SSL) aims to train machine learning models using unlabeled data by formulating pretext tasks that encourage the model to learn useful representations. Current research focuses on improving SSL's performance and generalization across diverse data types (images, audio, graphs, point clouds) and downstream tasks, employing techniques like contrastive learning, masked autoencoders, and generative models within various architectures such as transformers and convolutional neural networks. These advancements are significant because they reduce the reliance on expensive and time-consuming data labeling, enabling the development of robust models for applications ranging from medical image analysis and speech recognition to geospatial AI and protein function prediction. The efficiency gains from SSL are also a key focus, with research exploring optimal model and data sizes for given computational budgets.

Papers

July 25, 2022

Dynamic Channel Selection in Self-Supervised Learning
Tarun Krishna, Ayush K. Rai, Yasser A. D. Djilali, Alan F. Smeaton, Kevin McGuinness, Noel E. O'Connor
Self Supervised Learning Self Supervised Self Supervision Self Supervised Model Self Supervised Approach ImageNet LT Channel Selection

July 24, 2022

Explored An Effective Methodology for Fine-Grained Snake Recognition
Yong Huang, Aderon Huang, Wei Zhu, Yanming Fang, Jinghua Feng
Fine Grained Self Supervised Learning Fine Grained Visual Fine Grained Recognition

July 23, 2022

Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis
Gregory Holste, Evangelos K. Oikonomou, Bobak J. Mortazavi, Zhangyang Wang, Rohan Khera
Contrastive Learning Self Supervised Learning Self Supervised Pretraining Self Supervised Contrastive Learning Echocardiogram Video

July 22, 2022

Scale dependant layer for self-supervised nuclei encoding
Peter Naylor, Yao-Hung Hubert Tsai, Marick Laé, Makoto Yamada
Self Supervised Learning Visual Analogue Scale Nucleus Annotation Independent Layer

July 20, 2022

July 17, 2022

July 16, 2022

July 12, 2022

July 11, 2022

Patch-level instance-group discrimination with pretext-invariant learning for colitis scoring
Ziang Xu, Sharib Ali, Soumya Gupta, Simon Leedham, James E East, Jens Rittscher
Self Supervised Learning Endoscopic Image Instance Discrimination Ulcerative Colitis

July 10, 2022

Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentation
Ashraful Islam, Ben Lundell, Harpreet Sawhney, Sudipta Sinha, Peter Morales, Richard J. Radke
Semantic Segmentation Self Supervised Learning Data Detection Contrastive Loss Self Supervised Learning Method COCO Object Detection Urban Scene Segmentation

July 8, 2022

Pixel-level Correspondence for Self-Supervised Learning from Video
Yash Sharma, Yi Zhu, Chris Russell, Thomas Brox
Self Supervised Learning Optical Flow Source Video Supervised Baseline Pixel Correspondence DEnse Contrastive

July 7, 2022

July 6, 2022

Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network
Li Sun, Ke Yu, Kayhan Batmanghelich
Graph Neural Network Self Supervised Learning Self Supervised Medical Image Self Supervised Representation

Self Supervised Learning

Papers

Dynamic Channel Selection in Self-Supervised Learning

Explored An Effective Methodology for Fine-Grained Snake Recognition

Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis

Scale dependant layer for self-supervised nuclei encoding

End-to-End and Self-Supervised Learning for ComParE 2022 Stuttering Sub-Challenge

What Do We Maximize in Self-Supervised Learning?

Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition

Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR

Self-Supervised-RCNN for Medical Image Segmentation with Limited Data Annotation

Multi-Modal Unsupervised Pre-Training for Surgical Operating Room Workflow Analysis

On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning

Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning

Synergistic Self-supervised and Quantization Learning

Dual Contrastive Learning for Spatio-temporal Representation

Patch-level instance-group discrimination with pretext-invariant learning for colitis scoring

Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentation

Pixel-level Correspondence for Self-Supervised Learning from Video

An Embedding-Dynamic Approach to Self-supervised Learning

Vision Transformers: State of the Art and Research Challenges

Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network