3 accepted papers
End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder extracts hidden features from raw sensor data, and the decoder outputs the ego-vehicle's future trajectories or actions. Under such a p…
Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks. In this work, we consider a general and yet under-explored incremental learning problem in which both t…
We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incremental learning with limited memory and aim to achieve a better stability-plasticity trade-off. To this end, we propose a nov…