Related papers: Speed Co-Augmentation for Unsupervised Audio-Visua…

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…

Collaborative training can improve the accuracy of a model for a user by trading off the model's bias (introduced by using data from other users who are potentially different) against its variance (due to the limited amount of data on any…

Children learn to build a visual representation of the world from unsupervised exploration and we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a…

Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this…

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Self-supervised contrastive learning has emerged as a powerful tool in machine learning and computer vision to learn meaningful representations from unlabeled data. Meanwhile, its empirical success has encouraged many theoretical studies to…

Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent…

Learning from multiple modalities, such as audio and video, offers opportunities for leveraging complementary information, enhancing robustness, and improving contextual understanding and performance. However, combining such modalities…

Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the…

Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising…

Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…

Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap…

Self-supervised visual pretraining has shown significant progress recently. Among those methods, SimCLR greatly advanced the state of the art in self-supervised and semi-supervised learning on ImageNet. The input feature representations for…

Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to…

The abundance and ease of utilizing sound, along with the fact that auditory clues reveal so much about what happens in the scene, make the audio-visual space a perfectly intuitive choice for self-supervised representation learning.…

Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, online data are growing constantly, highlighting the…

Handwritten text and scene text suffer from various shapes and distorted patterns. Thus training a robust recognition model requires a large amount of data to cover diversity as much as possible. In contrast to data collection and…