the archive
#lightweight cnn
2 resultscs.CV2019
Full-Stack Filters to Build Minimum Viable CNNs
Kai Han, Yunhe Wang, Yixing Xu +3
The paper proposes full‑stack convolution filters combined with orthogonal binary masks to generate many diverse sub‑filters, allowing a CNN to keep only a few full‑stack filters a…
#model compression#lightweight cnn#filter pruning#edge devices
cs.CV2019
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Yuenan Hou, Zheng Ma, Chunxiao Liu +1
The paper introduces Self Attention Distillation (SAD), a knowledge‑distillation technique that uses a model’s own attention maps as free supervision to improve lightweight lane‑de…
#lane detection#knowledge distillation#attention mechanisms#lightweight cnn