3 citations · 14 across the 19 of their papers we have counts for
19 papers
Nipping the Butterfly Effect in the Bud: Self-Output Fine-Tuning for Autoregressive Weather Prediction
Yun-Ye Cai, Hsuan-Tien Lin
Long-horizon weather forecasting is a fundamental challenge in atmospheric science, for which autoregressive Deep Learning Weather Prediction (DLWP) has emerged as the primary para…
Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
Tan-Ha Mai, Chao-Kai Chiang, Han-Hwa Shih +3
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain…
Expanding the Role of Diffusion Models for Robust Classifier Training
Pin-Han Huang, Shang-Tse Chen, Hsuan-Tien Lin
Incorporating diffusion-generated synthetic data into adversarial training (AT) has been shown to substantially improve the training of robust image classifiers. In this work, we e…
Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
Tan-Ha Mai, Hsuan-Tien Lin
In this paper, we investigate the challenges of complementary-label learning (CLL), a specialized form of weakly-supervised learning (WSL) where models are trained with labels indi…
libcll: an Extendable Python Toolkit for Complementary-Label Learning
Nai-Xuan Ye, Tan-Ha Mai, Hsiu-Hsuan Wang +2
Complementary-label learning (CLL) is a weakly supervised learning paradigm for multiclass classification, where only complementary labels -- indicating classes an instance does no…
SLIM: Spuriousness Mitigation with Minimal Human Annotations
Xiwei Xuan, Ziquan Deng, Hsuan-Tien Lin +1
Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such corr…
CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference
Vo Nguyen Le Duy, Hsuan-Tien Lin, Ichiro Takeuchi
We propose a novel statistical method for testing the results of anomaly detection (AD) under domain adaptation (DA), which we call CAD-DA -- controllable AD under DA. The distinct…
From SMOTE to Mixup for Deep Imbalanced Classification
Wei-Chao Cheng, Tan-Ha Mai, Hsuan-Tien Lin
Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic min…
Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
Paul Kuo-Ming Huang, Si-An Chen, Hsuan-Tien Lin
Score-based generative models (SGMs) are a popular family of deep generative models that achieve leading image generation quality. Early studies extend SGMs to tackle class-conditi…
An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasets
Po-Yi Lu, Yi-Jie Cheng, Chun-Liang Li +1
Active Learning (AL) addresses the crucial challenge of enabling machines to efficiently gather labeled examples through strategic queries. Among the many AL strategies, Uncertaint…
Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation
Wei-I Lin, Gang Niu, Hsuan-Tien Lin +1
Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain in…
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
Oscar Chew, Hsuan-Tien Lin, Kai-Wei Chang +1
Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumst…
CLImage: Human-Annotated Datasets for Complementary-Label Learning
Hsiu-Hsuan Wang, Tan-Ha Mai, Nai-Xuan Ye +2
Complementary-label learning (CLL) is a weakly-supervised learning paradigm that aims to train a multi-class classifier using only complementary labels, which indicate classes to w…
Semi-Supervised Domain Adaptation with Source Label Adaptation
Yu-Chu Yu, Hsuan-Tien Lin
Semi-Supervised Domain Adaptation (SSDA) involves learning to classify unseen target data with a few labeled and lots of unlabeled target data, along with many labeled source data…
SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective
Xiwei Xuan, Ziquan Deng, Hsuan-Tien Lin +2
Researchers have proposed various methods for visually interpreting the Convolutional Neural Network (CNN) via saliency maps, which include Class-Activation-Map (CAM) based approac…
Reducing Training Sample Memorization in GANs by Training with Memorization Rejection
Andrew Bai, Cho-Jui Hsieh, Wendy Kan +1
Generative adversarial network (GAN) continues to be a popular research direction due to its high generation quality. It is observed that many state-of-the-art GANs generate sample…
Reduction from Complementary-Label Learning to Probability Estimates
Wei-I Lin, Hsuan-Tien Lin
Complementary-Label Learning (CLL) is a weakly-supervised learning problem that aims to learn a multi-class classifier from only complementary labels, which indicate a class to whi…
A Unified View of cGANs with and without Classifiers
Si-An Chen, Chun-Liang Li, Hsuan-Tien Lin
Conditional Generative Adversarial Networks (cGANs) are implicit generative models which allow to sample from class-conditional distributions. Existing cGANs are based on a wide ra…
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
Cheng-Yu Hsieh, Wei-I Lin, Miao Xu +3
The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where t…