papers
Publications (3)
cs.LG2022
Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector
Guoliang Lin, Hanlu Chu, Hanjiang Lai
Plasticity-stability dilemma is a main problem for incremental learning, where plasticity is referring to the ability to learn new knowledge, and stability retains the knowledge of…
cs.LG2024
Revisiting Few-Shot Learning from a Causal Perspective
Guoliang Lin, Yongheng Xu, Hanjiang Lai +1
Few-shot learning with -way -shot scheme is an open challenge in machine learning. Many metric-based approaches have been proposed to tackle this problem, e.g., the Matching…
cs.AI2024
Improving Entropy-Based Test-Time Adaptation from a Clustering View
Guoliang Lin, Hanjiang Lai, Yan Pan +1
Domain shift is a common problem in the realistic world, where training data and test data follow different data distributions. To deal with this problem, fully test-time adaptatio…