IVAICVLGNEAug 18, 2021

Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search

arXiv:2108.08910v260 citations
AI Analysis

This enables efficient super-resolution for mobile applications, though it is incremental as it builds on existing search and pruning techniques.

The authors tackled the challenge of deploying real-time super-resolution on mobile devices by combining neural architecture search with pruning search, achieving tens of milliseconds per frame for 720p resolution with competitive image quality (PSNR and SSIM) on a Samsung Galaxy S20.

Though recent years have witnessed remarkable progress in single image super-resolution (SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep learning methods are confronted with the computation and memory consumption issues in practice, especially for resource-limited platforms such as mobile devices. To overcome the challenge and facilitate the real-time deployment of SISR tasks on mobile, we combine neural architecture search with pruning search and propose an automatic search framework that derives sparse super-resolution (SR) models with high image quality while satisfying the real-time inference requirement. To decrease the search cost, we leverage the weight sharing strategy by introducing a supernet and decouple the search problem into three stages, including supernet construction, compiler-aware architecture and pruning search, and compiler-aware pruning ratio search. With the proposed framework, we are the first to achieve real-time SR inference (with only tens of milliseconds per frame) for implementing 720p resolution with competitive image quality (in terms of PSNR and SSIM) on mobile platforms (Samsung Galaxy S20).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes