6 papers · 1 filter
Rebalancing Multi-Label Class-Incremental Learning
Kaile Du, Yifan Zhou, Fan Lyu +5
Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledg…
Towards stable training of parallel continual learning
Li Yuepan, Fan Lyu, Yuyang Li +3
Parallel Continual Learning (PCL) tasks investigate the training methods for continual learning with multi-source input, where data from different tasks are learned as they arrive.…
Parameter-Selective Continual Test-Time Adaptation
Jiaxu Tian, Fan Lyu
Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approac…
Improving Data-aware and Parameter-aware Robustness for Continual Learning
Hanxi Xiao, Fan Lyu
The goal of Continual Learning (CL) task is to continuously learn multiple new tasks sequentially while achieving a balance between the plasticity and stability of new and old know…
Confidence Self-Calibration for Multi-Label Class-Incremental Learning
Kaile Du, Yifan Zhou, Fan Lyu +3
The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unav…
Variational Continual Test-Time Adaptation
Fan Lyu, Kaile Du, Yuyang Li +5
Continual Test-Time Adaptation (CTTA) task investigates effective domain adaptation under the scenario of continuous domain shifts during testing time. Due to the utilization of so…