Related papers: Diffusion Model Meets Non-Exemplar Class-Increment…
Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation…
This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the expense of…
Catastrophic forgetting remains a central obstacle for continual learning in neural models. Popular approaches -- replay and elastic weight consolidation (EWC) -- have limitations: replay requires a strong generator and is prone to…
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…
Continual learning aims to accumulate knowledge over a data stream while mitigating catastrophic forgetting. In Non-exemplar Class Incremental Learning (NECIL), forgetting arises during incremental optimization because old classes are…
This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared…
In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…
Few-shot class-incremental learning (FSCIL) aims to continually fit new classes with limited training data, while maintaining the performance of previously learned classes. The main challenges are overfitting the rare new training samples…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Few-shot class-incremental learning (FSCIL) aims at recognizing novel classes continually with limited novel class samples. A mainstream baseline for FSCIL is first to train the whole model in the base session, then freeze the feature…
Current mainstream deep learning techniques exhibit an over-reliance on extensive training data and a lack of adaptability to the dynamic world, marking a considerable disparity from human intelligence. To bridge this gap, Few-Shot…
The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…
Incremental brain tumor segmentation is critical for models that must adapt to evolving clinical datasets without retraining on all prior data. However, catastrophic forgetting, where models lose previously acquired knowledge, remains a…
New objects are continuously emerging in the dynamically changing world and a real-world artificial intelligence system should be capable of continual and effectual adaptation to new emerging classes without forgetting old ones. In view of…
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from…
Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing…
In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…
Class-incremental learning (CIL) for endoscopic image analysis is crucial for real-world clinical applications, where diagnostic models should continuously adapt to evolving clinical data while retaining performance on previously learned…
In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application…
Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature…