Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in …
W Pian, S Mo, Y Guo, Y Tian - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
In this paper, we introduce audio-visual class-incremental learning, a class-incremental learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual …
J Dong, W Liang, Y Cong… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Class-incremental learning (CIL) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However …
D Kim, B Han - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
A primary goal of class-incremental learning is to strike a balance between stability and plasticity, where models should be both stable enough to retain knowledge learned from …
Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn …
Z Hu, Y Li, J Lyu, D Gao… - Proceedings of the …, 2023 - openaccess.thecvf.com
The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is …
YM Tang, YX Peng, WS Zheng - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based …
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training …