Related papers: Bypassing Logits Bias in Online Class-Incremental …
Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for many real-world…
In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization…
Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume object classes of the overall framework are fixed over time. It…
In this paper, we address the incremental classifier learning problem, which suffers from catastrophic forgetting. The main reason for catastrophic forgetting is that the past data are not available during learning. Typical approaches keep…
A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural…
In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general framework for continual learning. We could further construct…
In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired…
Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain…
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…
In this work, we introduce JDCL - a new method for continual learning with generative rehearsal based on joint diffusion models. Neural networks suffer from catastrophic forgetting defined as abrupt loss in the model's performance when…
Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…
In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing…
In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the…
Catastrophic forgetting of previously learned knowledge while learning new tasks is a widely observed limitation of contemporary neural networks. Although many continual learning methods are proposed to mitigate this drawback, the main…
Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise. Recent approaches…
Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously…
In class-incremental learning (class-IL), models must classify all previously seen classes at test time without task-IDs, leading to task confusion. Despite being a key challenge, task confusion lacks a theoretical understanding. We present…
Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…
Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most…
In continual learning, there is a serious problem of catastrophic forgetting, in which previous knowledge is forgotten when a model learns new tasks. Various methods have been proposed to solve this problem. Replay methods which replay data…