Search Results for author: Yao Deng

Found 8 papers, 1 papers with code

Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer

no code implementations EAMT 2020 Hao Yang, Minghan Wang, Ning Xie, Ying Qin, Yao Deng

Compared with the commonly used NuQE baseline, BAL-QE achieves 47% (En-Ru) and 75% (En-De) of performance promotions.

NMT Transfer Learning

CUEING: a lightweight model to Capture hUman attEntion In driviNG

no code implementations25 May 2023 Linfeng Liang, Yao Deng, Yang Zhang, Jianchao Lu, Chen Wang, Quanzheng Sheng, Xi Zheng

Discrepancies in decision-making between Autonomous Driving Systems (ADS) and human drivers underscore the need for intuitive human gaze predictors to bridge this gap, thereby improving user trust and experience.

Autonomous Driving Decision Making +1

Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses

no code implementations5 Apr 2021 Yao Deng, Tiehua Zhang, Guannan Lou, Xi Zheng, Jiong Jin, Qing-Long Han

The rapid development of artificial intelligence, especially deep learning technology, has advanced autonomous driving systems (ADSs) by providing precise control decisions to counterpart almost any driving event, spanning from anti-fatigue safe driving to intelligent route planning.

Anomaly Detection Autonomous Driving +1

SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems

no code implementations12 Mar 2021 Chenhao Xu, Jiaqi Ge, Yong Li, Yao Deng, Longxiang Gao, Mengshi Zhang, Yong Xiang, Xi Zheng

Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy.

Edge-computing Federated Learning +1

An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models

1 code implementation6 Feb 2020 Yao Deng, Xi Zheng, Tianyi Zhang, Chen Chen, Guannan Lou, Miryung Kim

We derive several implications for system and middleware builders: (1) when adding a defense component against adversarial attacks, it is important to deploy multiple defense methods in tandem to achieve a good coverage of various attacks, (2) a blackbox attack is much less effective compared with a white-box attack, implying that it is important to keep model details (e. g., model architecture, hyperparameters) confidential via model obfuscation, and (3) driving models with a complex architecture are preferred if computing resources permit as they are more resilient to adversarial attacks than simple models.

Autonomous Driving

Cannot find the paper you are looking for? You can Submit a new open access paper.