相关论文: Contrastive Distillation Is a Sample-Efficient Sel…

Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains, leading to simple state-of-the-art algorithms for…

Self-supervised learning (SSL) has rapidly emerged as a transformative approach in computer vision, enabling the extraction of rich feature representations from vast amounts of unlabeled data and reducing reliance on costly manual…

Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…

We argue that the negative transfer problem occurring when the new task to learn arrives is an important problem that needs not be overlooked when developing effective Continual Reinforcement Learning (CRL) algorithms. Through comprehensive…

Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for…

In the image domain, excellent representations can be learned by inducing invariance to content-preserving transformations via noise contrastive learning. In this paper, we generalize contrastive learning to a wider set of transformations,…

Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

Self-supervised learning (SSL) has recently emerged as a powerful approach to learning representations from large-scale unlabeled data, showing promising results in time series analysis. The self-supervised representation learning can be…

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…

This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…

Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.…

In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically similar samples due to…

Despite substantial progress in multilingual extractive Question Answering (QA), models with high and uniformly distributed performance across languages remain challenging, especially for languages with limited resources. We study…

The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is…

Self-supervised methods have emerged as a promising avenue for representation learning in the recent years since they alleviate the need for labeled datasets, which are scarce and expensive to acquire. Contrastive methods are a popular…

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can capture useful…

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…