Complicated and deep neural network models can achieve high accuracy for image recognition. However, they require a huge amount of computations and model parameters, which are not suitable for mobile and embedded devices. Therefore, MobileNet was proposed, which can reduce the number of parameters and computational cost dramatically. The main idea of MobileNet is to use a depthwise separable convolution. Two hyper-parameters, a width multiplier and a resolution multiplier are used to the trade-off between the accuracy and the latency. In this paper, we propose a new architecture to improve the MobileNet. Instead of using the resolution multiplier, we use a depth multiplier and combine with either Fractional Max Pooling or the max pooling. Experimental results on CIFAR database show that the proposed architecture can reduce the amount of computational cost and increase the accuracy simultaneously.
MobileNets family of computer vision neural networks have fueled tremendous progress in the design and organization of resource-efficient architectures in recent years. New applications with stringent real-time requirements on highly constrained devices require further compression of MobileNets-like already compute-efficient networks. Model quantization is a widely used technique to compress and accelerate neural network inference and prior works have quantized MobileNets to 4-6 bits albeit with a modest to significant drop in accuracy. While quantization to sub-byte values (i.e. precision les…
University of Southern California（南加州大学）；Army Research Laboratory（陆军研究实验室）
On the basis of DefakeHop, an enhanced lightweight Deepfake detector called DefakeHop++ is proposed in this work. The improvements lie in two areas. First, DefakeHop examines three facial regions (i.e., two eyes and mouth) while DefakeHop++ includes eight more landmarks for broader coverage. Second, for discriminant features selection, DefakeHop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT). In DefakeHop++, rich spatial and spectral features are first derived from facial regions and landmarks automa…
Xi’an Jiaotong University（西安交通大学）；Tencent AI Lab（腾讯人工智能实验室）；Australian National University（澳大利亚国立大学）
Effective and Efficient spatio-temporal modeling is essential for action recognition. Existing methods suffer from the trade-off between model performance and model complexity. In this paper, we present a novel Spatio-Temporal Hybrid Convolution Network (denoted as "STH") which simultaneously encodes spatial and temporal video information with a small parameter cost. Different from existing works that sequentially or parallelly extract spatial and temporal information with different convolutional layers, we divide the input channels into multiple groups and interleave the spatial and temporal …
Robust and Real-Time Bangladeshi Currency Recognition: A Dual-Stream MobileNet and EfficientNet Approach
Department of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh（奈卡利科学与技术大学信息与通信工程系）；Department of Computer and Communication Engineering, International Islamic University Chittagong, Chattogram, Bangladesh（国际伊斯兰大学柴坦 Nagpur 分校计算机与通信工程系）；School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, USA（密西根南方大学计算机科学与工程学院）；Department of CSE, Netrokona University, Netrokona, Bangladesh（奈托克纳大学计算机科学与工程系）
Lovely Professional University（洛弗利专业大学）；Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Maharaja Agrasen Institute of Technology（马哈拉贾·阿格拉森技术学院）；University of Economics Ho Chi Minh City（胡志明市经济大学）
Breast cancer is a common cancer for women. Early detection of breast cancer can considerably increase the survival rate of women. This paper mainly focuses on transfer learning process to detect breast cancer. Modified VGG (MVGG), residual network, mobile network is proposed and implemented in this paper. DDSM dataset is used in this paper. Experimental results show that our proposed hybrid transfers learning model (Fusion of MVGG16 and ImageNet) provides an accuracy of 88.3% where the number of epoch is 15. On the other hand, only modified VGG 16 architecture (MVGG 16) provides an accuracy 8…
Hybrid Quantum Neural Networks for Enhanced Breast Cancer Thermographic Classification: A Novel Quantum-Classical Integration Approach
Faculty of Computing（计算学院）；Universiti Teknologi Malaysia（技术大学）；Faculty of Science and Technology（科学与技术学院）；Universitas Muhammadiyah Sidoarjo（穆罕默德大学西多亚罗乔）；Department of Information System（信息系统系）；Universitas Siber Jakarta（西巴克大学）
