1 code implementation • CVPR 2023 • Shao-Yuan Lo, Poojan Oza, Sumanth Chennupati, Alejandro Galindo, Vishal M. Patel
Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target data.
no code implementations • 25 Feb 2023 • Shaoyan Pan, Shao-Yuan Lo, Min Huang, Chaoqiong Ma, Jacob Wynne, Tonghe Wang, Tian Liu, Xiaofeng Yang
In this work, we propose an adversarial attack-based data augmentation method to improve the deep-learning-based segmentation algorithm for the delineation of Organs-At-Risk (OAR) in abdominal Computed Tomography (CT) to facilitate radiation therapy.
no code implementations • 30 Jul 2022 • Shao-Yuan Lo, Wei Wang, Jim Thomas, Jingjing Zheng, Vishal M. Patel, Cheng-Hao Kuo
In this paper, we propose a novel UDA method for MDE, referred to as Learning Feature Decomposition for Adaptation (LFDA), which learns to decompose the feature space into content and style components.
1 code implementation • 18 Feb 2022 • Shao-Yuan Lo, Vishal M. Patel
Adversarial Training (AT) has been considered to be the most successful adversarial defense approach.
1 code implementation • 25 Aug 2021 • Shao-Yuan Lo, Poojan Oza, Vishal M. Patel
To this end, we propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples.
1 code implementation • 23 Jan 2021 • Shao-Yuan Lo, Vishal M. Patel
In this paper, we propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples.
1 code implementation • 8 Dec 2020 • Shao-Yuan Lo, Jeya Maria Jose Valanarasu, Vishal M. Patel
Adversarial robustness of deep neural networks is an extensively studied problem in the literature and various methods have been proposed to defend against adversarial images.
no code implementations • 17 Sep 2020 • Shao-Yuan Lo, Vishal M. Patel
In this paper, we propose a novel attack method against video recognition models, Multiplicative Adversarial Videos (MultAV), which imposes perturbation on video data by multiplication.
no code implementations • 11 Sep 2020 • Shao-Yuan Lo, Vishal M. Patel
With a multiple BN structure, each BN brach is responsible for learning the distribution of a single perturbation type and thus provides more precise distribution estimations.
no code implementations • 23 Jul 2019 • Shao-Yuan Lo, Hsueh-Ming Hang
The proposed method has an accuracy close to the RGB model at about the same network complexity.
Ranked #81 on Semantic Segmentation on Cityscapes val
no code implementations • 22 Jul 2019 • Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan, Jing-Jhih Lin
Several studies leverage a semantic segmentation network to extract robust lane features, but few of them can distinguish different types of lanes.
1 code implementation • 24 Sep 2018 • Shang-Wei Hung, Shao-Yuan Lo, Hsueh-Ming Hang
It includes a sub-network to process depth maps and employs luminance images to assist the depth information in processes.
Ranked #8 on Real-Time Semantic Segmentation on Cityscapes val
4 code implementations • 17 Sep 2018 • Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan, Jing-Jhih Lin
Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots.
Ranked #10 on Semantic Segmentation on CamVid
no code implementations • 11 Sep 2018 • Ping-Rong Chen, Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan, Jing-Jhih Lin
Lane mark detection is an important element in the road scene analysis for Advanced Driver Assistant System (ADAS).
Ranked #14 on Semantic Segmentation on CamVid