I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation

arXiv:2403.18490v1 Announce Type: new
Abstract: This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring knowledge between the intermediate layers of teacher (cumbersome model) and student (compact model). For knowledge extraction, we exploit class prototypes derived from feature maps. To facilitate knowledge transfer, we employ a triplet loss in order to minimize intra-class variances and maximize inter-class variances between teacher …

abstract arxiv class compact cs.cv distillation focus image intermediate knowledge paper segmentation semantic type