Related papers: Generative Feature Replay For Class-Incremental Le…
When humans perform inductive learning, they often enhance the process with background knowledge. With the increasing availability of well-formed collaborative knowledge bases, the performance of learning algorithms could be significantly…
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…
We propose an approach to address two issues that commonly occur during training of unsupervised GANs. First, since GANs use only a continuous latent distribution to embed multiple classes or clusters of data, they often do not correctly…
Non-exemplar class-incremental learning (NECIL) is to resist catastrophic forgetting without saving old class samples. Prior methodologies generally employ simple rules to generate features for replaying, suffering from large distribution…
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay -- by concurrently training externally…
The fact that image datasets are often imbalanced poses an intense challenge for deep learning techniques. In this paper, we propose a method to restore the balance in imbalanced images, by coalescing two concurrent methods, generative…
In this paper, we address the problem of distillation-based class-incremental learning with a single head. A central theme of this task is to learn new classes that arrive in sequential phases over time while keeping the model's capability…
In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…
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…
We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks. We employ a classifier learned in the past to complement training examples rather than simply play a…
Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available. However, this…
This paper addresses the challenge of incremental learning in growing graphs with increasingly complex tasks. The goal is to continuously train a graph model to handle new tasks while retaining proficiency in previous tasks via memory…
In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data…
Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is…
Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on…
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…
Continual Anomaly Detection (CAD) enables anomaly detection models in learning new classes while preserving knowledge of historical classes. CAD faces two key challenges: catastrophic forgetting and segmentation of small anomalous regions.…
Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…
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…
Federated Class Incremental Learning (FCIL) aims to collaboratively process continuously increasing incoming tasks across multiple clients. Among various approaches, data replay has become a promising solution, which can alleviate…