Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even for common smartphone AI hardware, not to mention more constrained smart TV platforms that are often supporting INT8 inference only. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. For this, the participants were provided with the DIV2K dataset and trained quantized models to do an efficient 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated NPU capable of accelerating quantized neural networks. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

/pdf/real-time-quantized-image-super-resolution-on-mobile-npus-2py2h7xu51.pdf

Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report

As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos. In this Mobile AI challenge, the target was to develop an end-to-end deep learning-based image signal processing (ISP) pipeline that can replace classical hand-crafted ISPs and achieve nearly real-time performance on smartphone NPUs. For this, the participants were provided with a novel learned ISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102-megapixel medium format camera. The runtime of all models was evaluated on the MediaTek Dimensity 1000+ platform with a dedicated AI processing unit capable of accelerating both floating-point and quantized neural networks. The proposed solutions are fully compatible with the above NPU and are capable of processing Full HD photos under 60-100 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.

/pdf/learned-smartphone-isp-on-mobile-npus-with-deep-learning-1g8vf668cf.pdf

Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report

Image denoising is one of the most critical problems in mobile photo processing. While many solutions have been proposed for this task, they are usually working with synthetic data and are too computationally expensive to run on mobile devices. To address this problem, we introduce 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. For this, the participants were provided with a novel large-scale dataset consisting of noisy-clean image pairs captured in the wild. The runtime of all models was evaluated on the Samsung Exynos 2100 chipset with a powerful Mali GPU capable of accelerating floating-point and quantized neural networks. The proposed solutions are fully compatible with any mobile GPU and are capable of processing 480p resolution images under 40-80 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

/pdf/fast-camera-image-denoising-on-mobile-gpus-with-deep-4t2z43muim.pdf

Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report

This study proposes a novel framework to improve intrusion detection system (IDS) performance based on the data collected from the Internet of things (IoT) environments. The developed framework relies on deep learning and metaheuristic (MH) optimization algorithms to perform feature extraction and selection. A simple yet effective convolutional neural network (CNN) is implemented as the core feature extractor of the framework to learn better and more relevant representations of the input data in a lower-dimensional space. A new feature selection mechanism is proposed based on a recently developed MH method, called Reptile Search Algorithm (RSA), which is inspired by the hunting behaviors of the crocodiles. The RSA boosts the IDS system performance by selecting only the most important features (an optimal subset of features) from the extracted features using the CNN model. Several datasets, including KDDCup-99, NSL-KDD, CICIDS-2017, and BoT-IoT, were used to assess the IDS system performance. The proposed framework achieved competitive performance in classification metrics compared to other well-known optimization methods applied for feature selection problems.

/pdf/intrusion-detection-system-for-iot-based-on-deep-learning-2uqfcz0o.pdf

Intrusion Detection System for IoT Based on Deep Learning and Modified Reptile Search Algorithm

Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms. For this, the participants were provided with a large-scale CamSDD dataset consisting of more than 11K images belonging to the 30 most important scene categories. The runtime of all models was evaluated on the popular Apple Bionic A11 platform that can be found in many iOS devices. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms while achieving a top-3 accuracy of more than 98%. A detailed description of all models developed in the challenge is provided in this paper.

/pdf/fast-and-accurate-quantized-camera-scene-detection-on-4raypzclri.pdf

Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report

Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services. While many solutions have been proposed for this task, the majority of them are too computationally expensive to run on portable devices with limited hardware resources. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a real-time performance on mobile GPUs. The participants were provided with the REDS dataset and trained their models to do an efficient 4X video upscaling. The runtime of all models was evaluated on the OPPO Find X2 smartphone with the Snapdragon 865 SoC capable of accelerating floating-point networks on its Adreno GPU. The proposed solutions are fully compatible with any mobile GPU and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

/pdf/real-time-video-super-resolution-on-smartphones-with-deep-7oq4ldseqr.pdf

Xu Tianyu

Papers

Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report

Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report