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