相关论文: CroMo-Mixup: Augmenting Cross-Model Representation…

In-Context Learning (ICL) enhances the performance of large language models (LLMs) with demonstrations. However, obtaining these demonstrations primarily relies on manual effort. In most real-world scenarios, users are often unwilling or…

Self-supervised learning (SSL) has recently shown notable success in various visual tasks. However, in terms of discriminability, SSL is still not on par with supervised learning (SL). This paper identifies a key issue, the ``crowding…

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained…

Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features…

Continual learning (CL) aims to empower machine learning models to learn continually from new data, while building upon previously acquired knowledge without forgetting. As models have evolved from small to large pre-trained architectures,…

Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables continuous model adaptation, but most existing approaches either…

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained…

Medical image segmentation has significantly benefitted thanks to deep learning architectures. Furthermore, semi-supervised learning (SSL) has recently been a growing trend for improving a model's overall performance by leveraging abundant…

Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically. Continual Learning (CL) approaches seek to bridge this gap by facilitating the transfer of knowledge to both previous tasks…

Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance model performance, particularly in data-limited scenarios. However, this approach introduces a trade-off…

Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting…

The primary goal of continual learning (CL) task in medical image segmentation field is to solve the "catastrophic forgetting" problem, where the model totally forgets previously learned features when it is extended to new categories…

Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SSL methods applied to single-cell data, we present…

The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different…

In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and…

Self-supervised learning (SSL) learns high-quality representations from large pools of unlabeled training data. As datasets grow larger, it becomes crucial to identify the examples that contribute the most to learning such representations.…

Continual learning aims to create artificial neural networks capable of accumulating knowledge and skills through incremental training on a sequence of tasks. The main challenge of continual learning is catastrophic interference, wherein…

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient…

Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is…

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear what characteristics of their representations lead to high downstream accuracies. In this work, we characterize properties that SSL representations…