Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of ac...
详细信息
ISBN:
(纸本)9781728138572
Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of accuracy with a little awareness of computational efficiency. In this paper, we introduce LiteSeg, a lightweight architecture for semantic image segmentation. In this work, we explore a new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) and apply short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model. LiteSeg architecture is introduced and tested with multiple backbone networks as Darknet19, MobileNet, and ShuffleNet to provide multiple trade-offs between accuracy and computational cost. The proposed model LiteSeg, with MobileNetV2 as a backbone network, achieves an accuracy of 67.81% mean intersection over union at 161 frames per second with 640x360 resolution on the Cityscapes dataset.
Deep neural network (DNN) is hard to understand because the objective loss function is defined on the last layer, not directly on the hidden layers. To best understand DNN, we interpret the forwardpropagation and back...
详细信息
ISBN:
(纸本)9783030033354;9783030033347
Deep neural network (DNN) is hard to understand because the objective loss function is defined on the last layer, not directly on the hidden layers. To best understand DNN, we interpret the forwardpropagation and back-propagation of DNN as two network structures, fp-DNN and bp-DNN. Then we introduce the direct loss function for hidden layers of fp-DNN and bp-DNN, which gives a way to interpret the fp-DNN as an encoder and bp-DNN as a decoder. Using this interpretation of DNN, we do experiments to analyze that fp-DNN learns to encode discriminant features in the hidden layers with the supervision of bp-DNN. Further, we use bp-DNN to visualize and explain DNN. Our experiments and analyses show the proposed interpretation of DNN is a good tool to understand and analyze the DNN.
Over the years `synchro-ballistic' photographic techniques have been used to aid the scientist and engineer in obtaining data of fast moving events. With the availability of `gated video' a new technique, `Bal...
详细信息
ISBN:
(纸本)0819415979
Over the years `synchro-ballistic' photographic techniques have been used to aid the scientist and engineer in obtaining data of fast moving events. With the availability of `gated video' a new technique, `Ballistic Videography' has emerged. The purpose of this discussion is to review the principles of synchro-ballistic photography and discuss the use of high speed gated video to simplify and increase date yield.
暂无评论