Related papers: On the Discrimination and Consistency for Exemplar…
To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming…
Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetting with task priors, \ie using task identity or a subset of…
The continual learning setting aims to learn new tasks over time without forgetting the previous ones. The literature reports several significant efforts to tackle this problem with limited or no access to previous task data. Among such…
Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data…
Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic forgetting (CF), recent studies highlight that the…
Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…
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 federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical…
Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. Recently, a pioneer claims that the commonly used replay-based method in…
Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VLMs, we need not only to prevent the catastrophic forgetting…
Few Shot Class Incremental Learning (FSCIL) with few examples per class for each incremental session is the realistic setting of continual learning since obtaining large number of annotated samples is not feasible and cost effective. We…
This paper investigates a new, practical, but challenging problem named Non-exemplar Online Class-incremental continual Learning (NO-CL), which aims to preserve the discernibility of base classes without buffering data examples and…
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommendation systems, E-commerce platforms, etc. can be represented…
Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental…
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…
Class-incremental learning (CIL) in medical image-guided diagnosis requires retaining prior diagnostic knowledge while adapting to newly emerging disease categories, which is critical for scalable clinical deployment. This problem is…
Deep neural networks (DNNS) excel at learning from static datasets but struggle with continual learning, where data arrives sequentially. Catastrophic forgetting, the phenomenon of forgetting previously learned knowledge, is a primary…
Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may not always cover the most informative samples, which largely…
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…
Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation…