ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Ma, Ningning; Zhang, Xiangyu; Zheng, Haitao; Sun, Jian

doi:10.1007/978-3-030-01264-9_8

Cited by 4,332 publications

(2,830 citation statements)

References 49 publications

Supporting

Mentioning

2,381

Contrasting

Unclassified

Order By: Relevance

“…In contrast to the inverted bottleneck in MobileNetv2, the GE Layer has one more 3 × 3 convolution. However, this layer is also friendly to the computation cost and memory access cost (Ma et al, 2018;Sandler et al, 2018), because the 3 × 3 convolution is specially optimized in the CUDNN library (Chetlur et al, 2014;Ma et al, 2018). Meanwhile, because of this layer, the GE Layer has higher feature expression ability than the inverted bottleneck.…”

Section: Gather-and-expansion Layermentioning

confidence: 99%

BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation

Wang

Peng³

et al. 2018

Lecture Notes in Computer Science

1,960

1,263

View full text Add to dashboard Cite

The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable accuracy decrease. We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for real-time semantic segmentation. To this end, we propose an efficient and effective architecture with a good trade-off between speed and accuracy, termed Bilateral Segmentation Network (BiSeNet V2). This architecture involves: (i) a Detail Branch, with wide channels and shallow layers to capture low-level details and generate high-resolution feature representation; (ii) a Semantic Branch, with narrow channels and deep layers to obtain high-level semantic context. The Semantic Branch is lightweight due to reducing the channel capacity and a fast-downsampling strategy. Furthermore, we design a Guided Aggregation Layer to enhance mutual connections and fuse both types of feature representation. Besides, a booster training strategy is designed to improve the segmentation performance without any extra inference cost. Extensive quantitative and qualitative evaluations demonstrate that the pro-posed architecture performs favourably against a few state-of-the-art real-time semantic segmentation approaches. Specifically, for a 2,048×1,024 input, we achieve 72.6% Mean IoU on the Cityscapes test set with a speed of 156 FPS on one NVIDIA GeForce GTX 1080 Ti card, which is significantly faster than existing methods, yet we achieve better segmentation accuracy. Code and trained models will be made publicly available.

show abstract

Section: Gather-and-expansion Layermentioning

confidence: 99%

BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation

Wang

Peng³

et al. 2018

Lecture Notes in Computer Science

1,960

1,263

View full text Add to dashboard Cite

show abstract

“…They visualize the feature maps extracted by different filters and view each filter as a visual unit focusing on different visual components.of the ResNet-50 [28], and meanwhile save more than 75% of parameters and 50% computational time. In the literature, approaches for compressing the deep networks can be classified into five categories: parameter pruning [26,29,30,31], parameter quantizing [32,33,34,35,36,37,38,39,40,41], low-rank parameter factorization [42,43,44,45,46], transferred/compact convolutional filters [47,48,49,50], and knowledge distillation [51,52,53,54,55,56]. The parameter pruning and quantizing mainly focus on eliminating the redundancy in the model parameters respectively by removing the redundant/uncritical ones or compressing the parameter space (e.g.…”

mentioning

confidence: 99%

Binary neural networks: A survey

Qin

Gong

Liu

et al. 2020

Pattern Recognition

415

171

View full text Add to dashboard Cite

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices.However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network.To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected.the heavy computation and storage still inevitably limit the applications of the deep CNNs in practice. Besides, due to the huge model parameter space, the prediction of the neural networks is usually viewed as a black-box, which brings great challenges to the interpretability of CNNs. Some works like [21,22,23] empirically explore the function of each layer in the network. They visualize the feature maps extracted by different filters and view each filter as a visual unit focusing on different visual components.of the ResNet-50 [28], and meanwhile save more than 75% of parameters and 50% computational time. In the literature, approaches for compressing the deep networks can be classified into five categories: parameter pruning [26,29,30,31], parameter quantizing [32,33,34,35,36,37,38,39,40,41], low-rank parameter factorization [42,43,44,45,46], transferred/compact convolutional filters [47,48,49,50], and knowledge distillation [51,52,53,54,55,56]. The parameter pruning and quantizing mainly focus on eliminating the redundancy in the model parameters respectively by removing the redundant/uncritical ones or compressing the parameter space (e.g. , from the floating-point weights to the integer ones). Low-rank factorization applies the matrix/tensor decomposition techniques to estimate the informative parameters using the proxy ones of small size. The compact convolutional filter based approaches rely on the carefullydesigned structural convolutional filters to reduce the storage and computation complexity. The knowledge distillation methods try to distill a more compact model to reproduce the output of a larger network.Among the existing network compression techniques, quantization based one serves as a promising and fast solution that yields highly compact models compared to their floating-point counterparts, by representing the network weights with very low precision. Along this direction, the most extreme quantization is binarization, the interest...

show abstract

“…Thus, the Depthwise-STFT separable layer has a lower space-time complexity when com-arXiv:2001.09912v1 [cs.CV] 27 Jan 2020 pared to the depthwise separable convolutions. Furthermore, we show experimentally that the proposed layer achieves better performance compared to the many state-of-the-art depthwise separable based models such as MobileNet [6,7] and ShuffleNet [8,9].…”

Section: Introductionmentioning

confidence: 93%

“…Recently, there has been a growing interest into developing space-time efficient neural networks for real time and resource restricted applications [10,6,7,9,8,11,12]. Depthwise Separable Convolutions.…”

Section: Related Workmentioning

confidence: 99%

“…As discussed in Section 1, depthwise separable convolutions significantly reduce the space-time complexity of convolutional neural networks (CNNs) when compared to the standard convolutions by partitioning the steps of learning spatial and channel correlations. Recently, many depthwise separable convolutions based networks have been introduced such as MobileNet [6,7], ShuffleNet [8,9], and Xception [13]. Note that with the reduced complexity in the network architectures, these networks achieve trade-off between accuracy and space-time complexity.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Depthwise-STFT Based Separable Convolutional Neural Networks

Kumawat

Raman

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is inspired by the fact that the Fourier coefficients can accurately represent important features such as edges in an image. It utilizes the Fourier coefficients computed (channelwise) in the 2D local neighborhood (e.g., 3 × 3) of each position of the input map to obtain the feature maps. The Fourier coefficients are computed using 2D Short Term Fourier Transform (STFT) at multiple fixed low frequency points in the 2D local neighborhood at each position. These feature maps at different frequency points are then linearly combined using trainable pointwise (1 × 1) convolutions. We show that the proposed layer outperforms the standard depthwise separable layer based models on the CIFAR-10 and CIFAR-100 image classification datasets with reduced space-time complexity.

show abstract

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Cited by 4,332 publications

References 49 publications

BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation

BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation

Binary neural networks: A survey

Depthwise-STFT Based Separable Convolutional Neural Networks

Contact Info

Product

Resources

About