<ul><li>Current knowledge distillation methods for semantic segmentation focus on guiding the student to imitate the teacher's knowledge within homogeneous architectures.</li><li>A generic knowledge distillation method for semantic segmentation from a heterogeneous perspective called HeteroAKD is proposed.</li><li>HeteroAKD eliminates the influence of architecture-specific information by projecting intermediate features of the teacher and student into an aligned logits space.</li><li>HeteroAKD outperforms state-of-the-art KD methods in facilitating distillation between heterogeneous architectures.</li></ul>

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

Discover more