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

arXiv: https://arxiv.org/abs/2105.08819 · HTML: https://mlsanity.com/paper/2105.08819/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 17 May 2021.

## Builds on (most cited first, 28 of 28)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://mlsanity.com/paper/1903.08066/) (2019)
- [NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2005.01996/) (2020)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [AI Benchmark: Running Deep Neural Networks on Android Smartphones](https://mlsanity.com/paper/1810.01109/) (2018)
- [Learning Filter Basis for Convolutional Neural Network Compression](https://mlsanity.com/paper/1908.08932/) (2019)
- [Rendering Natural Camera Bokeh Effect with Deep Learning](https://mlsanity.com/paper/2006.05698/) (2020)
- [NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results](https://mlsanity.com/paper/2005.04117/) (2020)
- [AIM 2020 Challenge on Learned Image Signal Processing Pipeline](https://mlsanity.com/paper/2011.04994/) (2020)
- [PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report](https://mlsanity.com/paper/1810.01641/) (2018)
- [WESPE: Weakly Supervised Photo Enhancer for Digital Cameras](https://mlsanity.com/paper/1709.01118/) (2017)
- [AIM 2020 Challenge on Rendering Realistic Bokeh](https://mlsanity.com/paper/2011.04988/) (2020)
- [T-Basis: a Compact Representation for Neural Networks](https://mlsanity.com/paper/2007.06631/) (2020)
- [Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency](https://mlsanity.com/paper/2004.12599/) (2020)
- [Controlling Information Capacity of Binary Neural Network](https://mlsanity.com/paper/2008.01438/) (2020)

## Built on by (most cited first, 10 of 10)

- [Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.05910/) (2022)
- [Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report](https://mlsanity.com/paper/2211.03885/) (2022)
- [Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report](https://mlsanity.com/paper/2211.04470/) (2022)
- [Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.05256/) (2022)
- [DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition](https://mlsanity.com/paper/2410.13663/) (2024)
- [Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection](https://mlsanity.com/paper/2504.09297/) (2025)
- [Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.06769/) (2022)
- [Properties that allow or prohibit transferability of adversarial attacks among quantized networks](https://mlsanity.com/paper/2405.09598/) (2024)
- [Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns](https://mlsanity.com/paper/2407.14831/) (2024)
- [Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices](https://mlsanity.com/paper/2407.19644/) (2024)

## Abstract (arXiv)

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.