Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the …
This paper focuses on the prevalent stage interference and stage performance imbalance of incremental learning. To avoid obvious stage learning bottlenecks, we propose a new …
Y Cui, W Deng, H Chen, L Liu - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
Given a model well-trained with a large-scale base dataset, few-shot class-incremental learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples …
Driven by practical needs, research on Class-Incremental Learning (CIL) has received more and more attentions in recent years. A technical challenge to be conquered by CIL methods …
D Yang, Y Zhou, X Hong, A Zhang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Modern object detectors are ill-equipped to incrementally learn new emerging object classes over time due to the well-known phenomenon of catastrophic forgetting. Due to data …
J Du, P Liu, CM Vong, C Chen, T Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Machine learning aims to generate a predictive model from a training dataset of a fixed number of known classes. However, many real-world applications (such as health …
Y Li, W Cao, W Xie, J Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Most existing methods for audio classification assume that the vocabulary of audio classes to be classified is fixed. When novel (unseen) audio classes appear, audio classification …
Y He, Y Chen, Y Jin, S Dong… - Proceedings of the …, 2024 - openaccess.thecvf.com
In this paper we focus on a challenging Online Task-Free Class Incremental Learning (OTFCIL) problem. Different from the existing methods that continuously learn the feature …