AI Benchmark: Running Deep Neural Networks on Android Smartphones

@inproceedings{Ignatov2018AIBR,
  title={AI Benchmark: Running Deep Neural Networks on Android Smartphones},
  author={Andrey D. Ignatov and Radu Timofte and William Chou and Ke Wang and Max Wu and Tim Hartley and Luc Van Gool},
  booktitle={ECCV Workshops},
  year={2018}
}
Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available… Expand
AI Benchmark: All About Deep Learning on Smartphones in 2019
TLDR
This paper evaluates the performance and compares the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference and discusses the recent changes in the Android ML pipeline. Expand
Low-level Optimizations for Faster Mobile Deep Learning Inference Frameworks
TLDR
This PhD research aims at providing a path for developers to help them choose the best methods and tools to do real-time inference on mobile devices and demonstrates that low-level software implementations chosen in frameworks, model conversion steps and parameters set in the framework have a big impact on performance and accuracy. Expand
AIoT Bench: Towards Comprehensive Benchmarking Mobile and Embedded Device Intelligence
TLDR
A benchmark suite, AIoT Bench, is proposed to evaluate the AI ability of mobile and embedded devices, which covers different application domains, e.g. image recognition, speech recognition and natural language processing. Expand
HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting
TLDR
HG-Caffe is presented, which supports GPUs with half precision and provides up to 20 times speedup with GPUs compared to the original implementations, and the peak memory usage is reduced to about 80%. Expand
PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones
TLDR
PhoneBit is proposed, a GPU-accelerated BNN inference engine for Android-based mobile devices that fully exploits the computing power of BNNs on mobile GPUs and provides a set of operator-level optimizations including locality-friendly data layout, bit packing with vectorization and layers integration for efficient binary convolution. Expand
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
TLDR
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. Expand
Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
TLDR
A benchmark suite, AIoTBench, which focuses on the evaluation of the inference abilities of mobile and embedded devices, and proposes two unified metrics as the AI scores: Valid Images Per Second (VIPS) and Valid FLOPs Per second (VOPS). Expand
Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report
TLDR
The first Mobile AI challenge is introduced, 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. Expand
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
TLDR
The target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a realtime performance on mobile GPUs and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. Expand
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
  • Andrey D. Ignatov, Kim Byeoung-su, +29 authors Feifei Chen
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
The first Mobile AI challenge is introduced, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 56 REFERENCES
RSTensorFlow: GPU Enabled TensorFlow for Deep Learning on Commodity Android Devices
TLDR
The result shows that although GPUs on the phones are capable of offering substantial performance gain in matrix multiplication on mobile devices, models that involve multiplication of large matrices can run much faster (approx. 3 times faster in experiments) due to GPU support. Expand
CNNdroid: GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android
TLDR
A GPU-accelerated library, dubbed CNNdroid, for execution of trained deep CNNs on Android-based mobile devices, which achieves up to 60X speedup and 130X energy saving on current mobile devices. Expand
Can Deep Learning Revolutionize Mobile Sensing?
TLDR
Preliminary answers to how the field of mobile sensing can best make use of advances in deep learning towards robust and efficient sensor inference are provided by prototyping a low-power Deep Neural Network inference engine that exploits both the CPU and DSP of a mobile device SoC. Expand
Cappuccino: Efficient CNN Inference Software Synthesis for Mobile System-on-Chips
TLDR
Cappuccino is presented, a framework for synthesis of efficient inference software targeting mobile system-on-chips (SoCs) and techniques for efficient parallelization of CNN inference targeting mobile SoCs are proposed, and the underlying tradeoffs are explored. Expand
A Quantization-Friendly Separable Convolution for MobileNets
TLDR
This work analyzed the root cause of quantization loss and proposed a quantization-friendly separable convolution architecture that can archive 8-bit inference top-1 accuracy and almost closed the gap to the float pipeline. Expand
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
TLDR
A quantization scheme is proposed that allows inference to be carried out using integer- only arithmetic, which can be implemented more efficiently than floating point inference on commonly available integer-only hardware. Expand
Caffe: Convolutional Architecture for Fast Feature Embedding
TLDR
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Expand
Real-time human activity recognition from accelerometer data using Convolutional Neural Networks
TLDR
A user-independent deep learning-based approach for online human activity classification using Convolutional Neural Networks for local feature extraction together with simple statistical features that preserve information about the global form of time series is presented. Expand
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
TLDR
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones. Expand
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
TLDR
This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization. Expand
...
1
2
3
4
5
...