Patent
Convolutional neural network with reduced complexity
Vasilcoi Andrei,Radu Petru,Marina Liviu,Trasnea Bogdan,Grigorescu Sorin Mihai +4 more
- 11 Nov 2020
TL;DR: In this paper, a convolutional neural network (CNN) is used for determining a driving context of a vehicle. But the method is not suitable for autonomous driving and it requires at least one non-trainable classifier (NTC) for assigning a class label.
read more
Abstract: The present invention is related to a convolutional neural network (CNN) and to method, a computer program, and an apparatus for determining a driving context of a vehicle, which make use of such a convolutional neural network (CNN). The convolutional neural network (CNN) comprises one or more convolutional layers (CL) and one or more pooling layers (PL). In addition, the convolutional neural network (CNN) employs at least one non-trainable classifier (NTC) for assigning a class label.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
References
Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification
TL;DR: This article proposes an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks and shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.
555
Top-Down Neural Attention by Excitation Backprop
Jianming Zhang,Zhe Lin,Jonathan Brandt,Xiaohui Shen,Stan Sclaroff +4 more
- 08 Oct 2016
TL;DR: A new backpropagation scheme, called Excitation Backprop, is proposed to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process, and the concept of contrastive attention is introduced to make the top- down attention maps more discriminative.
330
•Posted Content
Deep Grid Net (DGN): A Deep Learning System for Real-Time Driving Context Understanding
Liviu A. Marina,Bogdan Trasnea,Cocias Tiberiu,Andrei Vasilcoi,Florin Moldoveanu,Sorin Mihai Grigorescu +5 more
TL;DR: In this paper, a Deep Grid Net (DGN) is proposed for understanding the context in which an autonomous car is driving. And the predicted driving context is further used for switching between different driving strategies implemented within EB robinos, Elektrobit's Autonomous Driving software platform.
1
Classification of truck body types using a deep transfer learning approach
Reza Vatani Nezafat,Behrouz Salahshour,Mecit Cetin +2 more
- 01 Nov 2018
TL;DR: Results show that using a pre-trained model to extract low-level features of images increases the accuracy of the model significantly, even with a relatively small size of training data.
Related Papers (5)
Michael Blot,Matthieu Cord,Nicolas Thome +2 more
- 19 Aug 2016
Sojeong Ha,Jeong-Min Yun,Seungjin Choi +2 more
- 01 Oct 2015