3 papers
cs.CV2025
Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learning
Liang Bai, Hong Song, Jinfu Li +6
Real-world applications often face data privacy constraints and high acquisition costs, making the assumption of sufficient training data in incremental tasks unrealistic and leadi…
cs.CV2024
Efficient Non-Exemplar Class-Incremental Learning with Retrospective Feature Synthesis
Liang Bai, Hong Song, Yucong Lin +5
Despite the outstanding performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning from continuous data streams in real-world scen…
cs.CV2023
Refined Response Distillation for Class-Incremental Player Detection
Liang Bai, Hangjie Yuan, Tao Feng +2
Detecting players from sports broadcast videos is essential for intelligent event analysis. However, existing methods assume fixed player categories, incapably accommodating the re…