Self Supervised

Self-supervised learning (SSL) aims to train machine learning models using unlabeled data by designing pretext tasks that encourage the model to learn useful representations. Current research focuses on improving generalization, mitigating overfitting, and developing efficient architectures like transformers and CNNs for various modalities (images, audio, point clouds, fMRI data). SSL's significance lies in its ability to leverage vast amounts of readily available unlabeled data, leading to improved performance on downstream tasks and reducing the reliance on expensive and time-consuming manual labeling, particularly impacting fields like medical imaging, speech processing, and autonomous driving.

Papers

February 3, 2023

SPADE: Self-supervised Pretraining for Acoustic DisEntanglement
John Harvill, Jarred Barber, Arun Nair, Ramin Pishehvar
Self Supervised Self Supervised Approach Speech Representation Disentanglement Self Supervised Representation Room Acoustic Acoustic Representation Speech Domain

February 2, 2023

February 1, 2023

Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms
Shihan Ma, Jidong J. Yang
Self Supervised Feature Wise Self Supervised Learning Method Vehicle Image Self Supervised Paradigm Vehicle Type Classification

January 30, 2023

Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
Rongjie Huang, Jiawei Huang, Dongchao Yang, Yi Ren, Luping Liu, Mingze Li, Zhenhui Ye, Jinglin Liu, Xiang Yin, Zhou Zhao
Self Supervised Text to Audio Generation Audio Text Pair Contrastive Language Audio Pretraining Prompt Diffusion Generative Multimodal Model

January 28, 2023

January 27, 2023

January 25, 2023

A Method For Eliminating Contour Errors In Self-Encoder Reconstructed Images
Yonggang Li, Hao Zhang
Self Supervised Practical Method Contour Error Edge Information Twin Neural Network

January 23, 2023

January 22, 2023

Unifying Synergies between Self-supervised Learning and Dynamic Computation
Tarun Krishna, Ayush K Rai, Alexandru Drimbarean, Eric Arazo, Paul Albert, Alan F Smeaton, Kevin McGuinness, Noel E O'Connor
Knowledge Distillation Self Supervised Learning Self Supervised Large Pre Trained Model Emerging Synergy

January 18, 2023

Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
Andrej Janda, Brandon Wagstaff, Edwin G. Ng, Jonathan Kelly
Contrastive Learning Semantic Segmentation Point Cloud Self Supervised Self Supervised Pre Training Point Cloud Segmentation Image Data 3D Datasets Point Cloud Modality

January 17, 2023

January 12, 2023

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
Anas Mahmoud, Jordan S. K. Hu, Tianshu Kuai, Ali Harakeh, Liam Paull, Steven L. Waslander
Self Supervised Contrastive Loss Mutual Distillation 3d Representation 3D Semantic Segmentation Point Representation

January 11, 2023

January 5, 2023

Single-round Self-supervised Distributed Learning using Vision Transformer
Sangjoon Park, Ik-Jae Lee, Jun Won Kim, Jong Chul Ye
Deep Learning Vision Transformer Self Supervised Foundation Model Distributed Learning Multi Round Encrypted Vision Transformer

Self Supervised

Papers

SPADE: Self-supervised Pretraining for Acoustic DisEntanglement

Energy-Inspired Self-Supervised Pretraining for Vision Models

HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning

Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms

Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models

Deciphering the Projection Head: Representation Evaluation Self-supervised Learning

HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption

Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised Learning

Bayesian Self-Supervised Contrastive Learning

A Method For Eliminating Contour Errors In Self-Encoder Reconstructed Images

ECGAN: Self-supervised generative adversarial network for electrocardiography

A Simple Recipe for Competitive Low-compute Self supervised Vision Models

Unifying Synergies between Self-supervised Learning and Dynamic Computation

Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data

Vision Learners Meet Web Image-Text Pairs

Cross-domain Self-supervised Framework for Photoacoustic Computed Tomography Image Reconstruction

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss

Generative-Contrastive Learning for Self-Supervised Latent Representations of 3D Shapes from Multi-Modal Euclidean Input

Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing

Single-round Self-supervised Distributed Learning using Vision Transformer