相关论文: Hybrid Memory Replay: Blending Real and Distilled …

Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new…

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality…

Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e.,…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…

The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distributions. This scenario intensifies the fundamental problem of catastrophic forgetting,…

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely…

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…

In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KD-based methods are successfully used in CIL, but they often struggle…

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 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…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Class-incremental learning (CIL) enables continuous learning of new classes while mitigating catastrophic forgetting of old ones. For the performance breakthrough of CIL, it is essential yet challenging to effectively refine past knowledge…

Class Incremental Learning (CIL) aims to handle the scenario where data of novel classes occur continuously and sequentially. The model should recognize the sequential novel classes while alleviating the catastrophic forgetting. In the…

Rehearsal-based techniques are commonly used to mitigate catastrophic forgetting (CF) in Incremental learning (IL). The quality of the exemplars selected is important for this purpose and most methods do not ensure the appropriate diversity…

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To address this, some methods propose replaying data from previous…

Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…

As a front-burner problem in incremental learning, class incremental semantic segmentation (CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods have utilized knowledge distillation to transfer knowledge…

Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or domains, referred to…

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…