the archive
#edge devices
3 resultscs.CV2019
LFFD: A Light and Fast Face Detector for Edge Devices
Yonghao He, Dezhong Xu, Lifang Wu +3
The paper presents LFFD, a lightweight, anchor‑free, one‑stage face detector designed for edge devices, achieving high accuracy on benchmarks while running at high frame rates with…
#face detection#edge devices#lightweight models#anchor-free
cs.LG2019
Associative Convolutional Layers
Hamed Omidvar, Vahideh Akhlaghi, Massimo Franceschetti +1
The paper proposes an auxiliary network called a Convolutional Slice Generator that produces CNN filters from a low‑dimensional latent space, drastically reducing the number of tra…
#parameter efficiency#convolutional neural networks#model compression#edge devices
cs.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