no code implementations • 1 Jan 2021 • Pei-Hsin Wang, Sheng-Iou Hsieh, Shih-Chieh Chang, Yu-Ting Chen, Da-Cheng Juan, Jia-Yu Pan, Wei Wei
Current practices to apply temperature scaling assume either a fixed, or a manually-crafted dynamically changing schedule.
no code implementations • 25 Dec 2020 • Pei-Hsin Wang, Sheng-Iou Hsieh, Shih-Chieh Chang, Yu-Ting Chen, Jia-Yu Pan, Wei Wei, Da-Chang Juan
Temperature scaling has been widely used as an effective approach to control the smoothness of a distribution, which helps the model performance in various tasks.
no code implementations • 7 Jul 2020 • Li-Huang Tsai, Shih-Chieh Chang, Yu-Ting Chen, Jia-Yu Pan, Wei Wei, Da-Cheng Juan
In this paper, we propose a noise-agnostic method to achieve robust neural network performance against any noise setting.
no code implementations • 17 Nov 2019 • Hao-Yun Chen, Li-Huang Tsai, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in semantic segmentation.
2 code implementations • ICCV 2019 • Hao-Yun Chen, Jhao-Hong Liang, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model.
1 code implementation • ICLR 2019 • Hao-Yun Chen, Pei-Hsin Wang, Chun-Hao Liu, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
Although being a widely-adopted approach, using cross entropy as the primary objective exploits mostly the information from the ground-truth class for maximizing data likelihood, and largely ignores information from the complement (incorrect) classes.
no code implementations • 29 Aug 2018 • An-Chieh Cheng, Jin-Dong Dong, Chi-Hung Hsu, Shu-Huan Chang, Min Sun, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding.
no code implementations • ECCV 2018 • Yu-Ting Chen, Wen-Yen Chang, Hai-Lun Lu, Ting-Fan Wu, Min Sun
Recently, a few domain adaptation and active learning approaches have been proposed to mitigate the performance drop.
no code implementations • 27 Jun 2018 • Chi-Hung Hsu, Shu-Huan Chang, Jhao-Hong Liang, Hsin-Ping Chou, Chun-Hao Liu, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures.
no code implementations • 17 Dec 2017 • Yu-Ting Chen, Joseph Wang, Yannan Bai, Gregory Castañón, Venkatesh Saligrama
We present a novel framework for finding complex activities matching user-described queries in cluttered surveillance videos.
no code implementations • 14 Aug 2017 • You-Luen Lee, Da-Cheng Juan, Xuan-An Tseng, Yu-Ting Chen, Shih-Chieh Chang
When will a server fail catastrophically in an industrial datacenter?
9 code implementations • ICCV 2017 • Yi-Hsin Chen, Wei-Yu Chen, Yu-Ting Chen, Bo-Cheng Tsai, Yu-Chiang Frank Wang, Min Sun
Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases.
no code implementations • CVPR 2016 • Ziming Zhang, Yu-Ting Chen, Venkatesh Saligrama
In this paper, we propose training very deep neural networks (DNNs) for supervised learning of hash codes.
no code implementations • ICCV 2015 • Ziming Zhang, Yu-Ting Chen, Venkatesh Saligrama
In this context we propose a novel probability model and introduce latent {\em view-specific} and {\em view-shared} random variables to jointly account for the view-specific appearance and cross-view similarities among data instances.
no code implementations • 24 Oct 2014 • Ziming Zhang, Yu-Ting Chen, Venkatesh Saligrama
We first map each pixel of an image to a visual word using a codebook, which is learned in an unsupervised manner.
no code implementations • 2 May 2014 • Jing Qian, Jonathan Root, Venkatesh Saligrama, Yu-Ting Chen
The resulting anomaly detector is shown to be asymptotically optimal and adaptive in that for any false alarm rate alpha, its decision region converges to the alpha-percentile level set of the unknown underlying density.