28 citations · 82 across the 14 of their papers we have counts for
6 papers · 1 filter
Multi-path Neural Networks for On-device Multi-domain Visual Classification
Qifei Wang, Junjie Ke, Joshua Greaves +9
Learning multiple domains/tasks with a single model is important for improving data efficiency and lowering inference cost for numerous vision tasks, especially on resource-constra…
The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study
Xiyang Luo, Hossein Talebi, Feng Yang +2
Handling digital images is almost always accompanied by a lossy compression in order to facilitate efficient transmission and storage. This introduces an unavoidable tension betwee…
GIFnets: Differentiable GIF Encoding Framework
Innfarn Yoo, Xiyang Luo, Yilin Wang +2
Graphics Interchange Format (GIF) is a widely used image file format. Due to the limited number of palette colors, GIF encoding often introduces color banding artifacts. Traditiona…
Super-Resolving Commercial Satellite Imagery Using Realistic Training Data
Xiang Zhu, Hossein Talebi, Xinwei Shi +2
In machine learning based single image super-resolution, the degradation model is embedded in training data generation. However, most existing satellite image super-resolution meth…
Better Compression with Deep Pre-Editing
Hossein Talebi, Damien Kelly, Xiyang Luo +4
Could we compress images via standard codecs while avoiding visible artifacts? The answer is obvious -- this is doable as long as the bit budget is generous enough. What if the all…
Distortion Agnostic Deep Watermarking
Xiyang Luo, Ruohan Zhan, Huiwen Chang +2
Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference…