English
Related papers

Related papers: Shift-based Primitives for Efficient Convolutional…

200 papers

Quantized CNN inference on ultra-low-power MCUs incurs unnecessary computations in neurons that produce saturated output values. These values are too extreme and are eventually clamped to the boundaries allowed by the neuron. Often times,…

Systems and Control · Electrical Eng. & Systems 2026-02-27 Shiming Li , Luca Mottola , Yuan Yao , Stefanos Kaxiras

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt…

Computer Vision and Pattern Recognition · Computer Science 2020-02-05 Hefei Ling , Yangyang Qin , Li Zhang , Yuxuan Shi , Ping Li

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

Embedding Convolutional Neural Network (CNN) into edge devices for inference is a very challenging task because such lightweight hardware is not born to handle this heavyweight software, which is the common overhead from the modern…

Computer Vision and Pattern Recognition · Computer Science 2020-09-17 Ching-Chen Wang , Ching-Te Chiu , Jheng-Yi Chang

Recent works on neural network pruning advocate that reducing the depth of the network is more effective in reducing run-time memory usage and accelerating inference latency than reducing the width of the network through channel pruning. In…

Machine Learning · Computer Science 2023-06-05 Jinuk Kim , Yeonwoo Jeong , Deokjae Lee , Hyun Oh Song

There has been huge progress on video action recognition in recent years. However, many works focus on tweaking existing 2D backbones due to the reliance of ImageNet pretraining, which restrains the models from achieving higher efficiency…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Zhe Wang , Xulei Yang

Shot boundary detection (SBD) is an important first step in many video processing applications. This paper presents a simple modular convolutional neural network architecture that achieves state-of-the-art results on the RAI dataset with…

Computer Vision and Pattern Recognition · Computer Science 2019-06-11 Tomáš Souček , Jaroslav Moravec , Jakub Lokoč

Depthwise separable convolutions and frequency-domain convolutions are two recent ideas for building efficient convolutional neural networks. They are seemingly incompatible: the vast majority of operations in depthwise separable CNNs are…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Mark Buckler , Neil Adit , Yuwei Hu , Zhiru Zhang , Adrian Sampson

Fixed-point quantization and binarization are two reduction methods adopted to deploy Convolutional Neural Networks (CNN) on end-nodes powered by low-power micro-controller units (MCUs). While most of the existing works use them as…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Luca Mocerino , Andrea Calimera

Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Ji Lin , Wei-Ming Chen , Han Cai , Chuang Gan , Song Han

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in…

Neural and Evolutionary Computing · Computer Science 2019-05-30 Ghouthi Boukli Hacene , Carlos Lassance , Vincent Gripon , Matthieu Courbariaux , Yoshua Bengio

We address the problem that state-of-the-art Convolution Neural Networks (CNN) classifiers are not invariant to small shifts. The problem can be solved by the removal of sub-sampling operations such as stride and max pooling, but at a cost…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Ganesh Sundaramoorthi , Timothy E. Wang

Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight bit-shift operations. However, existing bit-shift networks…

Machine Learning · Computer Science 2022-04-12 Xiaoxuan Lou , Guowen Xu , Kangjie Chen , Guanlin Li , Jiwei Li , Tianwei Zhang

Customizing Convolution Neural Networks (CNN) for production use has been a challenging task for DL practitioners. This paper intends to expedite the model customization with a model hub that contains the optimized models tiered by their…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Linnan Wang , Chenhan Yu , Satish Salian , Slawomir Kierat , Szymon Migacz , Alex Fit Florea

We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Abhimanyu Dubey , Moitreya Chatterjee , Narendra Ahuja

A Capsule Network (CapsNet) is a relatively new classifier and one of the possible successors of Convolutional Neural Networks (CNNs). CapsNet maintains the spatial hierarchies between the features and outperforms CNNs at classifying images…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Pouya Shiri , Amirali Baniasadi

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened…

Computer Vision and Pattern Recognition · Computer Science 2016-08-10 Ke Yu , Chao Dong , Chen Change Loy , Xiaoou Tang

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input…

Computer Vision and Pattern Recognition · Computer Science 2018-07-26 Xin Wang , Fisher Yu , Zi-Yi Dou , Trevor Darrell , Joseph E. Gonzalez

Modern single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs. The problem on feature redundancy is well studied in visual recognition…

Image and Video Processing · Electrical Eng. & Systems 2022-08-18 Ying Nie , Kai Han , Zhenhua Liu , Chuanjian Liu , Yunhe Wang

Recent deep CNNs contain forward shortcut connections; i.e. skip connections from low to high layers. Reusing features from lower layers that have higher resolution (location information) benefit higher layers to recover lost details and…

Computer Vision and Pattern Recognition · Computer Science 2017-07-19 Abrar H. Abdulnabi , Stefan Winkler , Gang Wang
‹ Prev 1 8 9 10 Next ›