To compete with existing mobile architectures, MobileViG introduces Sparse Vision Graph Attention (SVGA), a fast token-mixing operator based on the principles of GNNs. However, MobileViG scales poorly with model size, falling at most 1% behind models with similar latency. This paper introduces Mobile Graph Convolution (MGC), a new vision graph neural network (ViG) module that solves this scaling problem. Our proposed mobile vision architecture, MobileViGv2, uses MGC to demonstrate the effectiveness of our approach. MGC improves on SVGA by increasing graph sparsity and introducing conditional positional encodings to the graph operation. Our smallest model, MobileViGv2-Ti, achieves a 77.7% top-1 accuracy on ImageNet-1K, 2% higher than MobileViG-Ti, with 0.9 ms inference latency on the iPhone 13 Mini NPU. Our largest model, MobileViGv2-B, achieves an 83.4% top-1 accuracy, 0.8% higher than MobileViG-B, with 2.7 ms inference latency. Besides image classification, we show that MobileViGv2 generalizes well to other tasks. For object detection and instance segmentation on MS COCO 2017, MobileViGv2-M outperforms MobileViG-M by 1.2 $AP^{box}$ and 0.7 $AP^{mask}$, and MobileViGv2-B outperforms MobileViG-B by 1.0 $AP^{box}$ and 0.7 $AP^{mask}$. For semantic segmentation on ADE20K, MobileViGv2-M achieves 42.9% $mIoU$ and MobileViGv2-B achieves 44.3% $mIoU$. Our code can be found at \url{https://github.com/SLDGroup/MobileViGv2}.
Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are spatially local. To learn global representations, self-attention-based vision trans-formers (ViTs) have been adopted. Unlike CNNs, ViTs are heavy-weight. In this paper, we ask the following question: is it possible to combine the strengths of CNNs and ViTs to build a light-weight and low latency network for mobile vision tasks? Towards this end, we introduce…
Mobile vision transformers (MobileViT) can achieve state-of-the-art performance across several mobile vision tasks, including classification and detection. Though these models have fewer parameters, they have high latency as compared to convolutional neural network-based models. The main efficiency bottleneck in MobileViT is the multi-headed self-attention (MHA) in transformers, which requires $O(k^2)$ time complexity with respect to the number of tokens (or patches) $k$. Moreover, MHA requires costly operations (e.g., batch-wise matrix multiplication) for computing self-attention, impacting l…
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to othe…
Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but its kernel size is often overlooked. In this paper, we systematically study the impact of different kernel sizes, and observe that combining the benefits of multiple kernel sizes can lead to better accuracy and efficiency. Based on this observation, we propose a new mixed depthwise convolution (MixConv), which naturally mixes up multiple kernel sizes in a single convolution. As a simple drop-in replacement of vanilla depthwise convolution, our MixConv improves the accuracy and efficiency for existing Mobil…
Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we present Mobile Convolutional Vision Transformer (MoCoViT), which improves in performance and efficiency by introducing transformer into mobile convolutional networks to leverage the benefits of both architectures. Different from recent works on vision transformer, the mobile transformer block in MoCoViT is carefully designed for mobile devices and is very lightweight, accomplished …
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet on ImageNet classification task, under the compu…
Deep Learning (DL) has become a crucial technology for Artificial Intelligence (AI). It is a powerful technique to automatically extract high-level features from complex data which can be exploited for applications such as computer vision, natural language processing, cybersecurity, communications, and so on. For the particular case of computer vision, several algorithms like object detection in real time videos have been proposed and they work well on Desktop GPUs and distributed computing platforms. However these algorithms are still heavy for mobile and embedded visual applications. The rap…
The Johns Hopkins University（约翰斯·霍普金斯大学）；Google Research（谷歌研究院）
This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack separate mobile convolution and transformer blocks, we effectively merge them into a MOAT block. Starting with a standard Transformer block, we replace its multi-layer perceptron with a mobile convolution block, and further reorder it before the self-attention operation. The mobile convolution block not only enhances the network representation capacity, but also produces better downsampled features. Our conceptually si…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Google（谷歌）
Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design pattern over a broad range of mobile accelerators by revisiting the usefulness of regular convolutions. We discover that regular convolutions are a potent component to boost the latency-accuracy trade-off for object detection on accelerators, provided that they are placed strategically in the network via neural architecture search. By incorporating regular conv…
Carnegie Mellon University（卡内基梅隆大学）；Volvo Construction Equipment（沃尔沃建筑设备）
Across a majority of pedestrian detection datasets, it is typically assumed that pedestrians will be standing upright with respect to the image coordinate system. This assumption, however, is not always valid for many vision-equipped mobile platforms such as mobile phones, UAVs or construction vehicles on rugged terrain. In these situations, the motion of the camera can cause images of pedestrians to be captured at extreme angles. This can lead to very poor pedestrian detection performance when using standard pedestrian detectors. To address this issue, we propose a Rotational Rectification Ne…
Huazhong University of Science and Technology（华中科技大学）；Tencent PCG（腾讯平台与内容事业群）；Fudan University（复旦大学）；Zhejiang University（浙江大学）
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named \textbf{To}ken \textbf{P}yramid Vision Trans\textbf{former} (\textbf{TopFormer}). The proposed \textbf{TopFormer} takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that o…
An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and MobileNetV2. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead. On ImageNet IL…
Tamkang University（淡江大学）；National Cheng Kung University（台湾成功大学）
With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image classification, object detection, semantic segmentation, etc.), state-of-the-art convolutional neural networks have introduced some concepts of Transformer. This proves that Transformer has a good prospect in the field of image recognition. After Vision Transformer was proposed, more and more works began to use self-attention to completely replace the convoluti…
The MINSU(Mobile Inventory and Scanning Unit) algorithm uses the computational vision analysis method to record the residual quantity/fullness of the cabinet. To do so, it goes through a five-step method: object detection, foreground subtraction, K-means clustering, percentage estimation, and counting. The input image goes through the object detection method to analyze the specific position of the cabinets in terms of coordinates. After doing so, it goes through the foreground subtraction method to make the image more focus-able to the cabinet itself by removing the background (some manual wor…
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially …
University of Oregon（俄勒冈大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Picsart AI Research (PAIR)（Picsart人工智能研究院）
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods. However, most adopt spatial MLPs which take fixed dimension inputs, therefore making it difficult to apply them to downstream tasks, such as object detection and semantic segmentation. Moreover, single-stage designs further limit performance in other computer vision tasks and fully connected layers bear heavy computation. To tackle these problems, we propose ConvMLP: a hierarchical Convolutional M…
MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive state-of-the-art results, the fusion block inside MobileViTv1-block, creates scaling challenges and has a complex learning task. We propose changes to the fusion block that are simple and effective to create MobileViTv3-block, which addresses the scaling and simplifies the learning task. Our proposed MobileViTv3-block used to create MobileViTv3-XXS, XS and S models outperform Mo…
Convolution neural networks are widely used for mobile applications. However, GPU convolution algorithms are designed for mini-batch neural network training, the single-image convolution neural network inference algorithm on mobile GPUs is not well-studied. After discussing the usage difference and examining the existing convolution algorithms, we proposed the HNTMP convolution algorithm. The HNTMP convolution algorithm achieves $14.6 \times$ speedup than the most popular \textit{im2col} convolution algorithm, and $2.30 \times$ speedup than the fastest existing convolution algorithm (direct co…
Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile and embedded vision applications. Many works try to build networks as small as possible while still have acceptable performance. The state-of-the-art architecture is MobileNets. They use Depthwise Separable Convolution (DWConvolution) in place of standard Convolution to reduce the size of networks. This paper describes an improved version of MobileNet, called…
Several recent studies have demonstrated that attention-based networks, such as Vision Transformer (ViT), can outperform Convolutional Neural Networks (CNNs) on several computer vision tasks without using convolutional layers. This naturally leads to the following questions: Can a self-attention layer of ViT express any convolution operation? In this work, we prove that a single ViT layer with image patches as the input can perform any convolution operation constructively, where the multi-head attention mechanism and the relative positional encoding play essential roles. We further provide a l…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Amazon Lab126（亚马逊Lab126）；Korea University（高丽大学）；Amazon Inc（亚马逊公司）
Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance. Although depthwise separable convolution can be an efficient module to approximate a standard convolution, it often leads to reduced representational power of networks. In this paper, under budget constraints such as computational cost (MAdds) and the parameter count, we propose a novel basic architectural block, ANTBlock. It boosts the representational power by modeling, in a high dimensional space, interdependency…
Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard "fully-connected" convolutions, these convolutions are more computationally economical. However, "sparsely-connected" convolutions block the inter-group information exchange, which induces severe performance degradation. To address this issue, we present two novel operations named merging and evolution to leverage the inter-group information. Our key idea is encoding the inter-group information with a…
The Chinese University of Hong Kong（香港中文大学）；SmartMore
We study the vision transformer structure in the mobile level in this paper, and find a dramatic performance drop. We analyze the reason behind this phenomenon, and propose a novel irregular patch embedding module and adaptive patch fusion module to improve the performance. We conjecture that the vision transformer blocks (which consist of multi-head attention and feed-forward network) are more suitable to handle high-level information than low-level features. The irregular patch embedding module extracts patches that contain rich high-level information with different receptive fields. The tra…
University of Rochester（罗切斯特大学）；Georgia Institute of Technology（佐治亚理工学院）；ARM Research（ARM研究院）
Continuous computer vision (CV) tasks increasingly rely on convolutional neural networks (CNN). However, CNNs have massive compute demands that far exceed the performance and energy constraints of mobile devices. In this paper, we propose and develop an algorithm-architecture co-designed system, Euphrates, that simultaneously improves the energy-efficiency and performance of continuous vision tasks. Our key observation is that changes in pixel data between consecutive frames represents visual motion. We first propose an algorithm that leverages this motion information to relax the number of ex…
Mobile UI understanding is important for enabling various interaction tasks such as UI automation and accessibility. Previous mobile UI modeling often depends on the view hierarchy information of a screen, which directly provides the structural data of the UI, with the hope to bypass challenging tasks of visual modeling from screen pixels. However, view hierarchies are not always available, and are often corrupted with missing object descriptions or misaligned structure information. As a result, despite the use of view hierarchies could offer short-term gains, it may ultimately hinder the appl…
We study performance characteristics of convolutional neural networks (CNN) for mobile computer vision systems. CNNs have proven to be a powerful and efficient approach to implement such systems. However, the system performance depends largely on the utilization of hardware accelerators, which are able to speed up the execution of the underlying mathematical operations tremendously through massive parallelism. Our contribution is performance characterization of multiple CNN-based models for object recognition and detection with several different hardware platforms and software frameworks, usin…
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. It addresses a key challenge raised by mobile vision: the cache must operate under video scene variation, while trading off among cacheability, overhead, and loss in model accuracy. At the input of a model, DeepCache discovers video temporal locality by exploiting the video's internal structure, for which it borrows proven heuristics from video compression; into the model, DeepCache propaga…
Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, \textit{e.g.}, attention mechanism, ViT-based models are generally times slower than lightweight convolutional networks. Therefore, the deployment of ViT for real-time applications is particularly challenging, especially on resource-constrained hardware such as mobile devices. Recent efforts try to reduce the computation complexity of ViT through network architecture search or hybrid design with Mobil…
Mobile vision systems such as smartphones, drones, and augmented-reality headsets are revolutionizing our lives. These systems usually run multiple applications concurrently and their available resources at runtime are dynamic due to events such as starting new applications, closing existing applications, and application priority changes. In this paper, we present NestDNN, a framework that takes the dynamics of runtime resources into account to enable resource-aware multi-tenant on-device deep learning for mobile vision systems. NestDNN enables each deep learning model to offer flexible resour…
In this paper, we present an OpenCL-based heterogeneous implementation of a computer vision algorithm -- image inpainting-based object removal algorithm -- on mobile devices. To take advantage of the computation power of the mobile processor, the algorithm workflow is partitioned between the CPU and the GPU based on the profiling results on mobile devices, so that the computationally-intensive kernels are accelerated by the mobile GPGPU (general-purpose computing using graphics processing units). By exploring the implementation trade-offs and utilizing the proposed optimization strategies at d…
We present the first publicly available Android framework to stream data from an event camera directly to a mobile phone. Today's mobile devices handle a wider range of workloads than ever before and they incorporate a growing gamut of sensors that make devices smarter, more user friendly and secure. Conventional cameras in particular play a central role in such tasks, but they cannot record continuously, as the amount of redundant information recorded is costly to process. Bio-inspired event cameras on the other hand only record changes in a visual scene and have shown promising low-power app…
Institute of Neuroinformatics, University of Zurich and ETH Zurich（苏黎世大学与苏黎世联邦理工学院神经信息学研究所）
The discrimination of human gestures using wearable solutions is extremely important as a supporting technique for assisted living, healthcare of the elderly and neurorehabilitation. This paper presents a mobile electromyography (EMG) analysis framework to be an auxiliary component in physiotherapy sessions or as a feedback for neuroprosthesis calibration. We implemented a framework that allows the integration of multisensors, EMG and visual information, to perform sensor fusion and to improve the accuracy of hand gesture recognition tasks. In particular, we used an event-based camera adapted …
We propose combining memory saving techniques with traditional U-Net architectures to increase the complexity of the models on the Brain Tumor Segmentation (BraTS) challenge. The BraTS challenge consists of a 3D segmentation of a 240x240x155x4 input image into a set of tumor classes. Because of the large volume and need for 3D convolutional layers, this task is very memory intensive. To address this, prior approaches use smaller cropped images while constraining the model's depth and width. Our 3D U-Net uses a reversible version of the mobile inverted bottleneck block defined in MobileNetV2, M…
Mobile Augmented Reality (MAR) is becoming an important cyber-physical system application given the ubiquitous availability of mobile phones. With the need to operate in unprepared environments, accurate and robust registration and tracking has become an important research problem to solve. In fact, when MAR is used for tele-interactive applications involving large distances, say from an accident site to insurance office, tracking at both the ends is desirable and further it is essential to appropriately fuse inertial and vision sensors data. In this paper, we present results and discuss some …
Omnidirectional lighting provides the foundation for achieving spatially-variant photorealistic 3D rendering, a desirable property for mobile augmented reality applications. However, in practice, estimating omnidirectional lighting can be challenging due to limitations such as partial panoramas of the rendering positions, and the inherent environment lighting and mobile user dynamics. A new opportunity arises recently with the advancements in mobile 3D vision, including built-in high-accuracy depth sensors and deep learning-powered algorithms, which provide the means to better sense and unders…
Beijing Normal University（北京师范大学）；University of Waterloo（滑铁卢大学）；EPFL（洛桑联邦理工学院）
Standard 3D convolution operations require much larger amounts of memory and computation cost than 2D convolution operations. The fact has hindered the development of deep neural nets in many 3D vision tasks. In this paper, we investigate the possibility of applying depthwise separable convolutions in 3D scenario and introduce the use of 3D depthwise convolution. A 3D depthwise convolution splits a single standard 3D convolution into two separate steps, which would drastically reduce the number of parameters in 3D convolutions with more than one order of magnitude. We experiment with 3D depthw…
