Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Ye, Chengxi"'
The discontinuous operations inherent in quantization and sparsification introduce obstacles to backpropagation. This is particularly challenging when training deep neural networks in ultra-low precision and sparse regimes. We propose a novel, robust
Externí odkaz:
http://arxiv.org/abs/2409.09245
Autor:
Qin, Danfeng, Leichner, Chas, Delakis, Manolis, Fornoni, Marco, Luo, Shixin, Yang, Fan, Wang, Weijun, Banbury, Colby, Ye, Chengxi, Akin, Berkin, Aggarwal, Vaibhav, Zhu, Tenghui, Moro, Daniele, Howard, Andrew
We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce the Universal Inverted Bottleneck (UIB) search block, a unified and flexib
Externí odkaz:
http://arxiv.org/abs/2404.10518
Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with
Externí odkaz:
http://arxiv.org/abs/2103.16634
Autor:
Ye, Chengxi, Evanusa, Matthew, He, Hua, Mitrokhin, Anton, Goldstein, Tom, Yorke, James A., Fermüller, Cornelia, Aloimonos, Yiannis
Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels are in eff
Externí odkaz:
http://arxiv.org/abs/1905.11926
We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an ef
Externí odkaz:
http://arxiv.org/abs/1903.07520
In this work we present a lightweight, unsupervised learning pipeline for \textit{dense} depth, optical flow and egomotion estimation from sparse event output of the Dynamic Vision Sensor (DVS). To tackle this low level vision task, we use a novel en
Externí odkaz:
http://arxiv.org/abs/1809.08625
We introduce Evenly Cascaded convolutional Network (ECN), a neural network taking inspiration from the cascade algorithm of wavelet analysis. ECN employs two feature streams - a low-level and high-level steam. At each layer these streams interact, su
Externí odkaz:
http://arxiv.org/abs/1807.00456
We explain that the difficulties of training deep neural networks come from a syndrome of three consistency issues. This paper describes our efforts in their analysis and treatment. The first issue is the training speed inconsistency in different lay
Externí odkaz:
http://arxiv.org/abs/1708.00631
LightNet is a lightweight, versatile and purely Matlab-based deep learning framework. The idea underlying its design is to provide an easy-to-understand, easy-to-use and efficient computational platform for deep learning research. The implemented fra
Externí odkaz:
http://arxiv.org/abs/1605.02766
For robots that have the capability to interact with the physical environment through their end effectors, understanding the surrounding scenes is not merely a task of image classification or object recognition. To perform actual tasks, it is critica
Externí odkaz:
http://arxiv.org/abs/1602.00032