Related papers: Continual Deep Active Learning for Medical Imaging…

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…

In image classification tasks, the ability of deep CNNs to deal with complex image data has proven to be unrivalled. However, they require large amounts of labeled training data to reach their full potential. In specialised domains such as…

A major challenge that prevents the training of DL models is the limited availability of accurately labeled data. This shortcoming is highlighted in areas where data annotation becomes a time-consuming and error-prone task. In this regard,…

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning…

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies…

To address the performance limitations of the Segment Anything Model (SAM) in specific domains, existing works primarily adopt adapter-based one-step adaptation paradigms. However, some of these methods are specific developed for specific…

Existing learning models often exhibit poor generalization when deployed across diverse scenarios. It is primarily due to that the underlying reference frame of the data varies with the deployment environment and settings. However, despite…

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing…

In this letter, we introduce deep active learning (AL) for multi-label classification (MLC) problems in remote sensing (RS). In particular, we investigate the effectiveness of several AL query functions for MLC of RS images. Unlike the…

Non-local attention module has been proven to be crucial for image restoration. Conventional non-local attention processes features of each layer separately, so it risks missing correlation between features among different layers. To…

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained…

We introduce Information Condensing Active Learning (ICAL), a batch mode model agnostic Active Learning (AL) method targeted at Deep Bayesian Active Learning that focuses on acquiring labels for points which have as much information as…

Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we…

Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy and Bayesian, often rely on an…

Continual learning the ability of a neural network to learn multiple sequential tasks without catastrophic forgetting remains a central challenge in developing adaptive artificial intelligence systems. While deep learning models achieve…

Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity. To achieve meaningful human-computer and human-robot interactions, multi-modal models of the users…

Continual learning (CL) - the ability to progressively acquire and integrate new concepts - is essential to intelligent systems to adapt to dynamic environments. However, deep neural networks struggle with catastrophic forgetting (CF) when…

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge.…

The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To…