1 code implementation • 30 Mar 2024 • Yan-Shuo Liang, Wu-Jun Li
Furthermore, InfLoRA designs this subspace to eliminate the interference of the new task on the old tasks, making a good trade-off between stability and plasticity.
no code implementations • CVPR 2023 • Yan-Shuo Liang, Wu-Jun Li
Besides the ability to overcome CF on old tasks, API also tries to evaluate the model's plasticity and then adaptively improve the model's plasticity for learning a new task if necessary.
no code implementations • 23 Sep 2022 • Yan-Shuo Liang, Wu-Jun Li
But class distribution in memory is critical for replay-based memory to get good performance, especially when the class distribution in data stream is highly imbalanced.
no code implementations • 29 Sep 2021 • Yan-Shuo Liang, Wu-Jun Li
Most existing replay-based methods focus on single-label problems in which each sample in the data stream has only one label.