27 citations · 49 across the 12 of their papers we have counts for
17 papers
Spatiotemporal Dynamics-Aware Industrial Anomaly Detection and Reasoning
S-Wei Chen, Siangyu Yang, Yi-Chen Jan +2
Industrial Anomaly Detection (IAD) is a long-established problem that aims to detect defects in industrial products during manufacturing for quality control. Most existing studies…
Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
Jaron Yeh, Yen-Wei Chang, Jiang Liu +1
Industrial anomaly detection (IAD) is evolving beyond conventional detection and localization toward multimodal inspection systems that can describe, explain, and reason about fine…
Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models
Jiacong Xu, Shao-Yuan Lo, Bardia Safaei +2
Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD…
Adaptive Batch Normalization Networks for Adversarial Robustness
Shao-Yuan Lo, Vishal M. Patel
Deep networks are vulnerable to adversarial examples. Adversarial Training (AT) has been a standard foundation of modern adversarial defense approaches due to its remarkable effect…
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
Shao-Yuan Lo, Poojan Oza, Sumanth Chennupati +2
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 da…
Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation
Shaoyan Pan, Shao-Yuan Lo, Min Huang +5
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)…
Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation
Shao-Yuan Lo, Wei Wang, Jim Thomas +3
Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical functions for robotic tasks such as localization, mapping and obstacle detection. Supe…
Exploring Adversarially Robust Training for Unsupervised Domain Adaptation
Shao-Yuan Lo, Vishal M. Patel
Unsupervised Domain Adaptation (UDA) methods aim to transfer knowledge from a labeled source domain to an unlabeled target domain. UDA has been extensively studied in the computer…
Adversarially Robust One-class Novelty Detection
Shao-Yuan Lo, Poojan Oza, Vishal M. Patel
One-class novelty detectors are trained with examples of a particular class and are tasked with identifying whether a query example belongs to the same known class. Most recent adv…
Error Diffusion Halftoning Against Adversarial Examples
Shao-Yuan Lo, Vishal M. Patel
Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs h…
Overcomplete Representations Against Adversarial Videos
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. Howe…
MultAV: Multiplicative Adversarial Videos
Shao-Yuan Lo, Vishal M. Patel
The majority of adversarial machine learning research focuses on additive attacks, which add adversarial perturbation to input data. On the other hand, unlike image recognition pro…
Defending Against Multiple and Unforeseen Adversarial Videos
Shao-Yuan Lo, Vishal M. Patel
Adversarial robustness of deep neural networks has been actively investigated. However, most existing defense approaches are limited to a specific type of adversarial perturbations…
Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks
Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan +1
Lane detection plays an important role in a self-driving vehicle. Several studies leverage a semantic segmentation network to extract robust lane features, but few of them can dist…
Exploring Semantic Segmentation on the DCT Representation
Shao-Yuan Lo, Hsueh-Ming Hang
Typical convolutional networks are trained and conducted on RGB images. However, images are often compressed for memory savings and efficient transmission in real-world application…
Efficient Road Lane Marking Detection with Deep Learning
Ping-Rong Chen, Shao-Yuan Lo, Hsueh-Ming Hang +2
Lane mark detection is an important element in the road scene analysis for Advanced Driver Assistant System (ADAS). Limited by the onboard computing power, it is still a challenge…
Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan +1
Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimati…