English
Related papers

Related papers: Augmentations vs Algorithms: What Works in Self-Su…

200 papers

Self-Supervised learning (SSL) with Joint-Embedding Architectures (JEA) has led to outstanding performances. All instantiations of this paradigm were trained using strong and well-established hand-crafted data augmentations, leading to the…

Machine Learning · Computer Science 2024-12-02 Théo Moutakanni , Maxime Oquab , Marc Szafraniec , Maria Vakalopoulou , Piotr Bojanowski

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning…

Computation and Language · Computer Science 2024-06-10 Guanting Dong , Hongyi Yuan , Keming Lu , Chengpeng Li , Mingfeng Xue , Dayiheng Liu , Wei Wang , Zheng Yuan , Chang Zhou , Jingren Zhou

Pseudo-labeling is a crucial technique in semi-supervised learning (SSL), where artificial labels are generated for unlabeled data by a trained model, allowing for the simultaneous training of labeled and unlabeled data in a supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Khanh-Binh Nguyen , Joon-Sung Yang

Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation…

Computer Vision and Pattern Recognition · Computer Science 2022-09-13 Prarthana Bhattacharyya , Chengjie Huang , Krzysztof Czarnecki

Speech representation learning plays a vital role in speech processing. Among them, self-supervised learning (SSL) has become an important research direction. It has been shown that an SSL pretraining model can achieve excellent performance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-20 Yi-Chen Chen , Shu-wen Yang , Cheng-Kuang Lee , Simon See , Hung-yi Lee

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Asad Ullah , Alessandro Ragano , Andrew Hines

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Florent Chiaroni , Mohamed-Cherif Rahal , Nicolas Hueber , Frederic Dufaux

In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these…

Computer Vision and Pattern Recognition · Computer Science 2019-01-23 Cecilia Summers , Michael J. Dinneen

With the progress of sensor technology in wearables, the collection and analysis of PPG signals are gaining more interest. Using Machine Learning, the cardiac rhythm corresponding to PPG signals can be used to predict different tasks such…

Signal Processing · Electrical Eng. & Systems 2022-12-20 Ramin Ghorbani , Marcel J. T. Reinders , David M. J. Tax

This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Reza Akbarian Bafghi , Nidhin Harilal , Claire Monteleoni , Maziar Raissi

Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn generalized underlying structure. In this work, we harness…

Machine Learning · Computer Science 2022-06-03 Kiran Karra , Chace Ashcraft , Cash Costello

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…

Information Retrieval · Computer Science 2023-11-28 Abhijit Anand , Jurek Leonhardt , Jaspreet Singh , Koustav Rudra , Avishek Anand

Self-supervised learning (SSL) has achieved great success in various areas including speech processing. Recently, it is proven that speech based SSL models are able to extract superior universal representations on a range of downstream…

Sound · Computer Science 2022-12-21 Changli Tang , Yujin Wang , Xie Chen , Wei-Qiang Zhang

Self-supervised learning (SSL) allows training data representations without a supervised signal and has become an important paradigm in machine learning. Most SSL methods employ the cosine similarity between embedding vectors and hence…

Machine Learning · Computer Science 2025-06-12 Andrew Draganov , Sharvaree Vadgama , Sebastian Damrich , Jan Niklas Böhm , Lucas Maes , Dmitry Kobak , Erik Bekkers

Reconstruction and joint embedding have emerged as two leading paradigms in Self Supervised Learning (SSL). Reconstruction methods focus on recovering the original sample from a different view in input space. On the other hand, joint…

Machine Learning · Computer Science 2025-10-15 Hugues Van Assel , Mark Ibrahim , Tommaso Biancalani , Aviv Regev , Randall Balestriero

Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning…

Machine Learning · Computer Science 2024-04-09 Kexin Zhang , Qingsong Wen , Chaoli Zhang , Rongyao Cai , Ming Jin , Yong Liu , James Zhang , Yuxuan Liang , Guansong Pang , Dongjin Song , Shirui Pan

Despite the impressive progress of self-supervised learning (SSL), its applicability to low-compute networks has received limited attention. Reported performance has trailed behind standard supervised pre-training by a large margin, barring…

Computer Vision and Pattern Recognition · Computer Science 2023-10-04 Fuwen Tan , Fatemeh Saleh , Brais Martinez

Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a great number of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-16 Zili Huang , Shinji Watanabe , Shu-wen Yang , Paola Garcia , Sanjeev Khudanpur

Semi-supervised learning (SSL) can improve model performance by leveraging unlabeled images, which can be collected from public image sources with low costs. In recent years, synthetic images have become increasingly common in public image…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Zerun Wang , Jiafeng Mao , Liuyu Xiang , Toshihiko Yamasaki

Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high…

Machine Learning · Computer Science 2025-01-22 Eklavya Sarkar , Mathew Magimai. -Doss