Autonomous driving requires a comprehensive understanding of the surroun...
Motion prediction is highly relevant to the perception of dynamic object...
Unlike the conventional Knowledge Distillation (KD), Self-KD allows a ne...
The teacher-free online Knowledge Distillation (KD) aims to train an ens...
In this report, we introduce our solution to the Occupancy and Flow
Pred...
Current Knowledge Distillation (KD) methods for semantic segmentation of...
Training Transformer-based models demands a large amount of data, while
...
Knowledge distillation is an effective approach to leverage a well-train...
In this paper, we propose a novel network design mechanism for efficient...