no code implementations • 13 Dec 2023 • Yuyang Sun, Huy H. Nguyen, Chun-Shien Lu, Zhiyong Zhang, Lu Sun, Isao Echizen
The growing diversity of digital face manipulation techniques has led to an urgent need for a universal and robust detection technology to mitigate the risks posed by malicious forgeries.
1 code implementation • CVPR 2023 • Yuan-Chih Chen, Chun-Shien Lu
To our knowledge, the study of weakly supervised learning from the perspective of data augmentation to deal with the WSI classification problem that suffers from lack of training data and imbalance of categories is relatively unexplored.
no code implementations • CVPR 2022 • Jia-Wei Chen, Chia-Mu Yu, Ching-Chia Kao, Tzai-Wei Pang, Chun-Shien Lu
Despite an increased demand for valuable data, the privacy concerns associated with sensitive datasets present a barrier to data sharing.
1 code implementation • CVPR 2021 • Jia-Wei Chen, Li-Ju Chen, Chia-Mu Yu, Chun-Shien Lu
However, the sensitive information in the datasets discourages data owners from releasing these datasets.
no code implementations • 1 Jan 2021 • Ting-An Yen, Chun-Shien Lu, Pau-Choo Chung
Inspired by the observation from the distribution properties of the features extracted by the CNNs in the feature space and their link to robustness, this work designs a novel training process called Manifold-Aware Training (MAT), which forces CNNs to learn compact features to increase robustness.
no code implementations • COLING 2020 • Wan-Hsuan Lin, Chun-Shien Lu
Secondly, we propose a task-agnostic semantics-measured module, which cooperates with the graph representation method, in order to (3) project an edge of a sentence-level graph to the space of semantic relevance with respect to the corresponding concept nodes.
no code implementations • 28 Nov 2020 • Ching-Chia Kao, Jhe-Bang Ko, Chun-Shien Lu
Theoretical analyses and experimental results indicate that our method is promising for classifier smoothing and robustness certification.
no code implementations • 22 Oct 2020 • Gang-Xuan Lin, Shih-Wei Hu, Chun-Shien Lu
By taking advantage of deep learning in accelerating optimization algorithms, together with the speedup strategy that using the momentum from all previous layers in the network, we propose a learning-based method, called QISTA-Net-s, to solve the sparse signal reconstruction problem.
no code implementations • ICLR 2020 • Yi Lin Sung, Sung-Hsien Hsieh, Soo-Chang Pei, Chun-Shien Lu
Unseen data, which are not samples from the distribution of training data and are difficult to collect, have exhibited importance in numerous applications, ({\em e. g.,} novelty detection, semi-supervised learning, and adversarial training).
1 code implementation • 18 Aug 2019 • Ching-Lun Tai, Sung-Hsien Hsieh, Chun-Shien Lu
Considering the fact that the one-bit CS is optimal for the direction estimation of signals under noise with a fixed bit budget and that the traditional CS is able to provide residue information and estimated signals, we focus on the design of greedy algorithms, which consist of the main steps of support detection and recovered signal update, for the hybrid CS in this paper.
no code implementations • ICLR 2019 • Yi-Lin Sung, Sung-Hsien Hsieh, Soo-Chang Pei, Chun-Shien Lu
DSGAN considers the scenario that the training samples of target distribution, $p_{t}$, are difficult to collect.
no code implementations • 24 Jan 2016 • Sung-Hsien Hsieh, Chun-Shien Lu, Soo-Chang Pei
Binary embedding of high-dimensional data aims to produce low-dimensional binary codes while preserving discriminative power.
no code implementations • 16 Sep 2015 • Sung-Hsien Hsieh, Chun-Shien Lu, and Soo-Chang Pei
Template matching is widely used for many applications in image and signal processing and usually is time-critical.