Related papers: Demystifying Catastrophic Forgetting in Two-Stage …
To better understand catastrophic forgetting, we study fitting an overparameterized linear model to a sequence of tasks with different input distributions. We analyze how much the model forgets the true labels of earlier tasks after…
Video instance segmentation (VIS) has gained significant attention for its capability in tracking and segmenting object instances across video frames. However, most of the existing VIS approaches unrealistically assume that the categories…
Class incremental learning(CIL) has attracted much attention, but most existing related works focus on fine-tuning the entire representation model, which inevitably results in much catastrophic forgetting. In the contrast, with a…
Existing federated learning methods have effectively dealt with decentralized learning in scenarios involving data privacy and non-IID data. However, in real-world situations, each client dynamically learns new classes, requiring the global…
Although the concept of catastrophic forgetting is straightforward, there is a lack of study on its causes. In this paper, we systematically explore and reveal three causes for catastrophic forgetting in Class Incremental Learning(CIL).…
Continual learning -- the ability to acquire knowledge incrementally without forgetting previous skills -- is fundamental to natural intelligence. While the human brain excels at this, artificial neural networks struggle with "catastrophic…
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…
Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…
Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better…
Neural networks notoriously suffer from the problem of catastrophic forgetting, the phenomenon of forgetting the past knowledge when acquiring new knowledge. Overcoming catastrophic forgetting is of significant importance to emulate the…
Incremental unlearning (IU) is critical for pre-trained models to comply with sequential data deletion requests, yet existing methods primarily suppress parameters or confuse knowledge without explicit constraints on both feature and…
Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated…
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…
Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…
This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of…
Generally intelligent agents exhibit successful behavior across problems in several settings. Endemic in approaches to realize such intelligence in machines is catastrophic forgetting: sequential learning corrupts knowledge obtained earlier…
In order to achieve Continual Learning (CL), the problem of catastrophic forgetting, one that has plagued neural networks since their inception, must be overcome. The evaluation of continual learning methods relies on splitting a known…
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. We focus on continual text classification under the class-incremental setting. Recent CL studies have identified…
Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates interfere with the dominant singular directions that encode essential pre-trained knowledge. We…
Efficient continual learning techniques have been a topic of significant research over the last few years. A fundamental problem with such learning is severe degradation of performance on previously learned tasks, known also as catastrophic…