Related papers: Balanced softmax cross-entropy for incremental lea…

Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory. The ratio fluctuation of new samples to old exemplars, which is caused by the variation…

Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user.…

Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the capacity to handle streams of visual information and the…

Neural network classifiers trained with cross-entropy loss achieve strong predictive accuracy but lack the capability to provide inherent predictive uncertainty estimates, thus requiring external techniques to obtain these estimates. In…

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a…

Deep networks have shown remarkable results in the task of object detection. However, their performance suffers critical drops when they are subsequently trained on novel classes without any sample from the base classes originally used to…

Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned, termed "catastrophic forgetting". Many state-of-the-art solutions to continual learning rely on biasing and/or…

A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline,…

In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned…

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Human being and different species of animals having the skills to gather, transferring knowledge, processing, fine-tune and generating information throughout their lifetime. The ability of learning throughout their lifespan is referred as…

Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We show that optimising the parameters of classification neural…

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to…

We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge…

When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing forgetting of old…

Deep learning models suffer from catastrophic forgetting of the classes in the older phases as they get trained on the classes introduced in the new phase in the class-incremental learning setting. In this work, we show that the effect of…

A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a…

Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The…

Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic…

Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting. Inter-class imbalance during training has been identified as a major cause of forgetting,…