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

September 13, 2022

SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds
Siddhant Garg, Mudit Chaudhary
Point Cloud Self Supervised Learning Transformer Based 3D Point Cloud Self Supervised Representation Learning Search Engine Result Page

September 10, 2022

Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species
Abubakar Siddique, Amy Tabb, Henry Medeiros
Convolutional Neural Network Self Supervised Learning Panoptic Segmentation Flower Detection

September 9, 2022

Self-supervised Learning for Heterogeneous Graph via Structure Information based on Metapath
Shuai Ma, Jian-wei Liu, Xin Zuo
Self Supervised Learning Heterogeneous Graph Node Representation Graph Data Graph Structure Information

September 8, 2022

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, Chang Yue, Fan Xiang, Yuling Cai, Hualong Ma, Yingjun Zhang, Guozhu Meng
Self Supervised Learning Supervised Learning Watermarking Method Encoder Side Backdoor Watermark Black Box Watermarking

September 7, 2022

September 2, 2022

August 31, 2022

August 30, 2022

August 26, 2022

The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation
Hugues Thomas, Jian Zhang, Timothy D. Barfoot
Self Supervised Learning Dynamic Scene Indoor Navigation Future Prediction Occupancy Grid Risk Heat Map

August 25, 2022

Clustering Egocentric Images in Passive Dietary Monitoring with Self-Supervised Learning
Jiachuan Peng, Peilun Shi, Jianing Qiu, Xinwei Ju, Frank P. -W. Lo, Xiao Gu, Wenyan Jia, Tom Baranowski, Matilda Steiner-Asiedu, Alex K. Anderson, Megan A McCrory, Edward Sazonov, Mingui Sun, Gary Frost, Benny Lo
Self Supervised Learning Wi Fi Sensing Intake Monitoring Dietary Assessment Wearable Camera

August 23, 2022

Transfer Learning Application of Self-supervised Learning in ARPES
Sandy Adhitia Ekahana, Genta Indra Winata, Y. Soh, Gabriel Aeppli, Radovic Milan, Ming Shi
Self Supervised Learning Transfer Learning Representation Learning Shot Learning Angle Resolved Photoemission

Self Supervised Learning

Papers

SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds

Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species

Self-supervised Learning for Heterogeneous Graph via Structure Information based on Metapath

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning

MimCo: Masked Image Modeling Pre-training with Contrastive Teacher

Improving Self-supervised Learning for Out-of-distribution Task via Auxiliary Classifier

Feature diversity in self-supervised learning

IMG2IMU: Translating Knowledge from Large-Scale Images to IMU Sensing Applications

Detection of diabetic retinopathy using longitudinal self-supervised learning

Self-Score: Self-Supervised Learning on Score-Based Models for MRI Reconstruction

BinImg2Vec: Augmenting Malware Binary Image Classification with Data2Vec

Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation

Sketching the Expression: Flexible Rendering of Expressive Piano Performance with Self-Supervised Learning

Domain Shift-oriented Machine Anomalous Sound Detection Model Based on Self-Supervised Learning

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning

Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond

Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised Learning

The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation

Clustering Egocentric Images in Passive Dietary Monitoring with Self-Supervised Learning

Transfer Learning Application of Self-supervised Learning in ARPES