3 papers
cs.RO2021
Incorporating Orientations into End-to-end Driving Model for Steering Control
Peng Wan, Zhenbo Song, Jianfeng Lu
In this paper, we present a novel end-to-end deep neural network model for autonomous driving that takes monocular image sequence as input, and directly generates the steering cont…
cs.LG2019
Generating Adversarial Examples With Conditional Generative Adversarial Net
Ping Yu, Kaitao Song, Jianfeng Lu
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples…
cs.CL2018
Double Path Networks for Sequence to Sequence Learning
Kaitao Song, Xu Tan, Di He +3
Encoder-decoder based Sequence to Sequence learning (S2S) has made remarkable progress in recent years. Different network architectures have been used in the encoder/decoder. Among…