Related papers: Randomized Neural Network with Adaptive Forward Re…
With the explosive growth of data, continual learning capability is increasingly important for neural networks. Due to catastrophic forgetting, neural networks inevitably forget the knowledge of old tasks after learning new ones. In visual…
Incremental class learning involves sequentially learning classes in bursts of examples from the same class. This violates the assumptions that underlie methods for training standard deep neural networks, and will cause them to suffer from…
Though neural networks have achieved much progress in various applications, it is still highly challenging for them to learn from a continuous stream of tasks without forgetting. Continual learning, a new learning paradigm, aims to solve…
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…
Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…
Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical…
Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks),…
Exemplar-free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in…
Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…
The domain of machine learning is confronted with a crucial research area known as class imbalance learning, which presents considerable hurdles in precise classification of minority classes. This issue can result in biased models where the…
In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online…
Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old…
Class-incremental learning (CIL) has emerged as a means to learn new classes incrementally without catastrophic forgetting of previous classes. Recently, CIL has undergone a paradigm shift towards dynamic architectures due to their superior…
As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions…
Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…
Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to…
With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distributions. However, CIL faces the core challenge of catastrophic…
We propose a novel continual learning method called Residual Continual Learning (ResCL). Our method can prevent the catastrophic forgetting phenomenon in sequential learning of multiple tasks, without any source task information except the…
In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…
Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks.…