Related papers: DER: Dynamically Expandable Representation for Cla…
We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify a…
Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, typically lasting less than half a second. Recognizing these subtle expressions is critical for applications in psychology, security, and…
Additive parameter updates, as used in gradient descent and its adaptive extensions, underpin most modern machine-learning optimization. Yet, such additive schemes often demand numerous iterations and intricate learning-rate schedules to…
Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…
Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- and plasticity --…
Incrementally training deep neural networks to recognize new classes is a challenging problem. Most existing class-incremental learning methods store data or use generative replay, both of which have drawbacks, while 'rehearsal-free'…
We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…
Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high…
Deep representation learning methods struggle with continual learning, suffering from both catastrophic forgetting of useful units and loss of plasticity, often due to rigid and unuseful units. While many methods address these two issues…
Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference…
Deep learning research aims at discovering learning algorithms that discover multiple levels of distributed representations, with higher levels representing more abstract concepts. Although the study of deep learning has already led to…
The use of episodic memory in continual learning has demonstrated effectiveness for alleviating catastrophic forgetting. In recent studies, gradient-based approaches have been developed to make more efficient use of compact episodic memory.…
Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources…
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…
Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…
Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence…
We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network,…
Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…
Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…