235 citations · 403 across the 4 of their papers we have counts for
4 papers
Scale-wise Convolution for Image Restoration
Yuchen Fan, Jiahui Yu, Ding Liu +1
While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Na…
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
Jiahui Yu, Thomas Huang
We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and…
Foreground-aware Image Inpainting
Wei Xiong, Jiahui Yu, Zhe Lin +4
Existing image inpainting methods typically fill holes by borrowing information from surrounding pixels. They often produce unsatisfactory results when the holes overlap with or to…
Slimmable Neural Networks
Jiahui Yu, Linjie Yang, Ning Xu +2
We present a simple and general method to train a single neural network executable at different widths (number of channels in a layer), permitting instant and adaptive accuracy-eff…