Related papers: AIR: Analytic Imbalance Rectifier for Continual Le…

Federated Class Incremental Learning (FCIL) aims to collaboratively process continuously increasing incoming tasks across multiple clients. Among various approaches, data replay has become a promising solution, which can alleviate…

Continual learning is a challenging problem in machine learning, especially for image classification tasks with imbalanced datasets. It becomes even more challenging when it involves learning new classes incrementally. One method for…

The proliferation of AI models in everyday devices has highlighted a critical challenge: prediction errors that degrade user experience. While existing solutions focus on error detection, they rarely provide efficient correction mechanisms,…

Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…

Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR.…

Consider a sequential active learning problem where, at each round, an agent selects a batch of unlabeled data points, queries their labels and updates a binary classifier. While there exists a rich body of work on active learning in this…

Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task…

Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new…

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex…

Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensive memory cost. In this work, targeted at these problems, we…

Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e.,…

Pedestrian attribute recognition is an important multi-label classification problem. Although the convolutional neural networks are prominent in learning discriminative features from images, the data imbalance in multi-label setting for…

Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge. Several approaches have been proposed in the literature, such as experience rehearsal,…

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…

Deep neural networks have demonstrated susceptibility to adversarial attacks. Adversarial defense techniques often focus on one-shot setting to maintain robustness against attack. However, new attacks can emerge in sequences in real-world…

This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based…

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distributions. This scenario intensifies the fundamental problem of catastrophic forgetting,…

Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data to predict the future values. However, in practical…

Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored past during training.…