68 citations · 400 across the 24 of their papers we have counts for
24 papers
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
Si-An Chen, Chun-Liang Li, Hsuan-Tien Lin
Generative Adversarial Networks (GANs) is a powerful family of models that learn an underlying distribution to generate synthetic data. Many existing studies of GANs focus on impro…
On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
Ching-Yuan Bai, Hsuan-Tien Lin, Colin Raffel +1
Many recent developments on generative models for natural images have relied on heuristically-motivated metrics that can be easily gamed by memorizing a small sample from the true…
Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination
Ashesh, Buo-Fu Chen, Treng-Shi Huang +3
Precipitation nowcasting is an important task for weather forecasting. Many recent works aim to predict the high rainfall events more accurately with the help of deep learning tech…
Cold-start Active Learning through Self-supervised Language Modeling
Michelle Yuan, Hsuan-Tien Lin, Jordan Boyd-Graber
Active learning strives to reduce annotation costs by choosing the most critical examples to label. Typically, the active learning strategy is contingent on the classification mode…
360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales
Ashesh, Chu-Song Chen, Hsuan-Tien Lin
Gaze estimation involves predicting where the person is looking at within an image or video. Technically, the gaze information can be inferred from two different magnification leve…
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin +1
In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions. Neverthe…
SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning
Chi-Chang Lee, Yu-Chen Lin, Hsuan-Tien Lin +2
Numerous noise adaptation techniques have been proposed to fine-tune deep-learning models in speech enhancement (SE) for mismatched noise environments. Nevertheless, adaptation to…
Learning from Label Proportions with Consistency Regularization
Kuen-Han Tsai, Hsuan-Tien Lin
The problem of learning from label proportions (LLP) involves training classifiers with weak labels on bags of instances, rather than strong labels on individual instances. The wea…
Benchmarking Tropical Cyclone Rapid Intensification with Satellite Images and Attention-based Deep Models
Ching-Yuan Bai, Buo-Fu Chen, Hsuan-Tien Lin
Rapid intensification (RI) of tropical cyclones often causes major destruction to human civilization due to short response time. It is an important yet challenging task to accurate…
Active Deep Q-learning with Demonstration
Si-An Chen, Voot Tangkaratt, Hsuan-Tien Lin +1
Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The…
Deep Learning with a Rethinking Structure for Multi-label Classification
Yao-Yuan Yang, Yi-An Lin, Hong-Min Chu +1
Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation c…
Compatibility Family Learning for Item Recommendation and Generation
Yong-Siang Shih, Kai-Yueh Chang, Hsuan-Tien Lin +1
Compatibility between items, such as clothes and shoes, is a major factor among customer's purchasing decisions. However, learning "compatibility" is challenging due to (1) broader…
Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
Hong-Min Chu, Kuan-Hao Huang, Hsuan-Tien Lin
We study multi-label classification (MLC) with three important real-world issues: online updating, label space dimensional reduction (LSDR), and cost-sensitivity. Current MLC algor…
Soft Methodology for Cost-and-error Sensitive Classification
Te-Kang Jan, Da-Wei Wang, Chi-Hung Lin +1
Many real-world data mining applications need varying cost for different types of classification errors and thus call for cost-sensitive classification algorithms. Existing algorit…
libact: Pool-based Active Learning in Python
Yao-Yuan Yang, Shao-Chuan Lee, Yu-An Chung +3
libact is a Python package designed to make active learning easier for general users. The package not only implements several popular active learning strategies, but also features…
Active Sampling of Pairs and Points for Large-scale Linear Bipartite Ranking
Wei-Yuan Shen, Hsuan-Tien Lin
Bipartite ranking is a fundamental ranking problem that learns to order relevant instances ahead of irrelevant ones. The pair-wise approach for bi-partite ranking construct a quadr…
Cost-Sensitive Reference Pair Encoding for Multi-Label Learning
Yao-Yuan Yang, Kuan-Hao Huang, Chih-Wei Chang +1
Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the pred…
Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation
Yu-An Chung, Shao-Wen Yang, Hsuan-Tien Lin
While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies,…
Can Active Learning Experience Be Transferred?
Hong-Min Chu, Hsuan-Tien Lin
Active learning is an important machine learning problem in reducing the human labeling effort. Current active learning strategies are designed from human knowledge, and are applie…
Automatic Bridge Bidding Using Deep Reinforcement Learning
Chih-Kuan Yeh, Hsuan-Tien Lin
Bridge is among the zero-sum games for which artificial intelligence has not yet outperformed expert human players. The main difficulty lies in the bidding phase of bridge, which r…
Cost-Sensitive Label Embedding for Multi-Label Classification
Kuan-Hao Huang, Hsuan-Tien Lin
Label embedding (LE) is an important family of multi-label classification algorithms that digest the label information jointly for better performance. Different real-world applicat…
Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning
Yu-An Chung, Hsuan-Tien Lin, Shao-Wen Yang
Deep learning has been one of the most prominent machine learning techniques nowadays, being the state-of-the-art on a broad range of applications where automatic feature extractio…
Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA
Chun-Liang Li, Hsuan-Tien Lin, Chi-Jen Lu
We study the problem of recovering the subspace spanned by the first principal components of -dimensional data under the streaming setting, with a memory bound of . T…
An Online Boosting Algorithm with Theoretical Justifications
Shang-Tse Chen, Hsuan-Tien Lin, Chi-Jen Lu
We study the task of online boosting--combining online weak learners into an online strong learner. While batch boosting has a sound theoretical foundation, online boosting deserve…