Related papers: Memory-Free Generative Replay For Class-Incrementa…
We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple state-of-the-art methods, we found vanilla experience…
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…
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…
Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after…
Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by…
Meta-learning models have two objectives. First, they need to be able to make predictions over a range of task distributions while utilizing only a small amount of training data. Second, they also need to adapt to new novel unseen tasks at…
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…
We introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model as new batches of photos in different appearances, styles, poses, and lighting are captured regularly.…
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…
Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging…
Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies.…
Incremental learning (IL) is an important task aimed at increasing the capability of a trained model, in terms of the number of classes recognizable by the model. The key problem in this task is the requirement of storing data (e.g. images)…
Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge. Several approaches have been developed in the literature to tackle the Continual Learning challenge. Among…
Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly…
We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning. Our framework addresses this challenging task…
Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a constant complexity of the deep model and an incremental…
Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of…
In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…
Continual learning refers to the ability to acquire and transfer knowledge without catastrophically forgetting what was previously learned. In this work, we consider \emph{few-shot} continual learning in classification tasks, and we propose…
Deep neural networks struggle to continually learn multiple sequential tasks due to catastrophic forgetting of previously learned tasks. Rehearsal-based methods which explicitly store previous task samples in the buffer and interleave them…