Angeline Pouget

TL;DR: In this article, the authors introduced the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs.

TL;DR: In this article, the authors proposed a novel camera scene detection dataset (CamSDD) containing more than 11k manually crawled images belonging to 30 different scene categories and proposed an efficient and NPU-friendly CNN model for this task.

TL;DR: A novel Camera Scene Detection Dataset (CamSDD) containing more than 11K manually crawled images belonging to 30 different scene categories is proposed and an efficient and NPU-friendly CNN model is proposed that demonstrates a top-3 accuracy of 99.5% on this dataset and achieves more than 200 FPS on the recent mobile SoCs.

TL;DR: In this article, the authors introduced the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs.

TL;DR: In this article , the authors propose an iterative factorizer for distributed block codes (SBCs), which introduces a threshold-based nonlinear activation, a conditional random sampling, and an $\ell_\infty$-based similarity metric.