b'Gang Niu'

research

∙ 08/12/2023

Multi-Label Knowledge Distillation

Existing knowledge distillation methods typically work by imparting the ...

0 Penghui Yang, et al. ∙

research

∙ 07/21/2023

Distribution Shift Matters for Knowledge Distillation with Webly Collected Images

Knowledge distillation aims to learn a lightweight student network from ...

0 Jialiang Tang, et al. ∙

research

∙ 07/12/2023

Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation

Generating unlabeled data has been recently shown to help address the fe...

0 Ruijiang Dong, et al. ∙

research

∙ 06/20/2023

A Universal Unbiased Method for Classification from Aggregate Observations

In conventional supervised classification, true labels are required for ...

0 Zixi Wei, et al. ∙

research

∙ 06/12/2023

Making Binary Classification from Multiple Unlabeled Datasets Almost Free of Supervision

Training a classifier exploiting a huge amount of supervised data is exp...

0 Yuhao Wu, et al. ∙

research

∙ 05/24/2023

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

Distribution shift (DS) may have two levels: the distribution itself cha...

0 Tongtong Fang, et al. ∙

research

∙ 05/15/2023

Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation

Complementary-label Learning (CLL) is a form of weakly supervised learni...

0 Wei-I Lin, et al. ∙

research

∙ 05/10/2023

Towards Effective Visual Representations for Partial-Label Learning

Under partial-label learning (PLL) where, for each training instance, on...

0 Shiyu Xia, et al. ∙

research

∙ 05/04/2023

Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning

Pseudo labeling is a popular and effective method to leverage the inform...

0 Ming-Kun Xie, et al. ∙

research

∙ 04/30/2023

Assessing Vulnerabilities of Adversarial Learning Algorithm through Poisoning Attacks

Adversarial training (AT) is a robust learning algorithm that can defend...

1 Jingfeng Zhang, et al. ∙

research

∙ 12/08/2022

Logit Clipping for Robust Learning against Label Noise

In the presence of noisy labels, designing robust loss functions is crit...

0 Hongxin Wei, et al. ∙

research

∙ 11/01/2022

Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks

Adversarial training (AT) with imperfect supervision is significant but ...

1 Jianan Zhou, et al. ∙

research

∙ 10/05/2022

FedMT: Federated Learning with Mixed-type Labels

In federated learning (FL), classifiers (e.g., deep networks) are traine...

4 Qiong Zhang, et al. ∙

research

∙ 06/15/2022

Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack

The AutoAttack (AA) has been the most reliable method to evaluate advers...

0 Ruize Gao, et al. ∙

research

∙ 06/06/2022

Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation

In label-noise learning, estimating the transition matrix has attracted ...

0 De Cheng, et al. ∙

research

∙ 04/07/2022

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

Supervised federated learning (FL) enables multiple clients to share the...

25 Nan Lu, et al. ∙

research

∙ 02/22/2022

On the Effectiveness of Adversarial Training against Backdoor Attacks

DNNs' demand for massive data forces practitioners to collect data from ...

1 Yinghua Gao, et al. ∙

research

∙ 02/01/2022

Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification

There is a fundamental limitation in the prediction performance that a m...

0 Takashi Ishida, et al. ∙

research

∙ 01/22/2022

PiCO: Contrastive Label Disambiguation for Partial Label Learning

Partial label learning (PLL) is an important problem that allows each tr...

0 Haobo Wang, et al. ∙

research

∙ 09/29/2021

Active Refinement for Multi-Label Learning: A Pseudo-Label Approach

The goal of multi-label learning (MLL) is to associate a given instance ...

0 Cheng-Yu Hsieh, et al. ∙

research

∙ 09/07/2021

Instance-dependent Label-noise Learning under a Structural Causal Model

Label noise will degenerate the performance of deep learning algorithms ...

0 Yu Yao, et al. ∙

research

∙ 06/30/2021

Understanding and Improving Early Stopping for Learning with Noisy Labels

The memorization effect of deep neural network (DNN) plays a pivotal rol...

0 Yingbin Bai, et al. ∙

research

∙ 06/30/2021

Local Reweighting for Adversarial Training

Instances-reweighted adversarial training (IRAT) can significantly boost...

0 Ruize Gao, et al. ∙

research

∙ 06/16/2021

Multi-Class Classification from Single-Class Data with Confidences

Can we learn a multi-class classifier from only data of a single class? ...

0 Yuzhou Cao, et al. ∙

research

∙ 06/15/2021

Probabilistic Margins for Instance Reweighting in Adversarial Training

Reweighting adversarial data during training has been recently shown to ...

0 Qizhou Wang, et al. ∙

research

∙ 06/11/2021

Adversarial Robustness through the Lens of Causality

The adversarial vulnerability of deep neural networks has attracted sign...

12 Yonggang Zhang, et al. ∙

research

∙ 06/11/2021

On the Robustness of Average Losses for Partial-Label Learning

Partial-label (PL) learning is a typical weakly supervised classificatio...

0 Jiaqi Lv, et al. ∙

research

∙ 06/09/2021

Reliable Adversarial Distillation with Unreliable Teachers

In ordinary distillation, student networks are trained with soft labels ...

1 Jianing Zhu, et al. ∙

research

∙ 06/01/2021

Instance Correction for Learning with Open-set Noisy Labels

The problem of open-set noisy labels denotes that part of training data ...

0 Xiaobo Xia, et al. ∙

research

∙ 06/01/2021

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

In learning with noisy labels, the sample selection approach is very pop...

0 Xiaobo Xia, et al. ∙

research

∙ 05/31/2021

NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?

Adversarial training (AT) based on minimax optimization is a popular lea...

1 Jingfeng Zhang, et al. ∙

research

∙ 02/13/2021

Learning from Similarity-Confidence Data

Weakly supervised learning has drawn considerable attention recently to ...

0 Yuzhou Cao, et al. ∙

research

∙ 02/10/2021

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

We investigate the adversarial robustness of CNNs from the perspective o...

1 Hanshu Yan, et al. ∙

research

∙ 02/08/2021

Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

In learning to discover novel classes(L2DNC), we are given labeled data ...

0 Haoang Chi, et al. ∙

research

∙ 02/06/2021

Understanding the Interaction of Adversarial Training with Noisy Labels

Noisy labels (NL) and adversarial examples both undermine trained models...

1 Jianing Zhu, et al. ∙

research

∙ 02/04/2021

Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization

Many weakly supervised classification methods employ a noise transition ...

11 Yivan Zhang, et al. ∙

research

∙ 02/04/2021

Provably End-to-end Label-Noise Learning without Anchor Points

In label-noise learning, the transition matrix plays a key role in build...

0 Xuefeng Li, et al. ∙

research

∙ 02/03/2021

Learning Diverse-Structured Networks for Adversarial Robustness

In adversarial training (AT), the main focus has been the objective and ...

1 Xuefeng Du, et al. ∙

research

∙ 02/01/2021

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification

To cope with high annotation costs, training a classifier only from weak...

0 Shida Lei, et al. ∙

research

∙ 01/14/2021

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

The drastic increase of data quantity often brings the severe decrease o...

0 Qizhou Wang, et al. ∙

research

∙ 12/02/2020

SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning

Deep learning with noisy labels is a challenging task. Recent prominent ...

0 Zhuowei Wang, et al. ∙

research

∙ 11/09/2020

A Survey of Label-noise Representation Learning: Past, Present and Future

Classical machine learning implicitly assumes that labels of the trainin...

0 Bo Han, et al. ∙

research

∙ 10/22/2020

Maximum Mean Discrepancy is Aware of Adversarial Attacks

The maximum mean discrepancy (MMD) test, as a representative two-sample ...

1 Ruize Gao, et al. ∙

research

∙ 10/05/2020

Pointwise Binary Classification with Pairwise Confidence Comparisons

Ordinary (pointwise) binary classification aims to learn a binary classi...

3 Lei Feng, et al. ∙

research

∙ 10/05/2020

Geometry-aware Instance-reweighted Adversarial Training

In adversarial machine learning, there was a common belief that robustne...

1 Jingfeng Zhang, et al. ∙

research

∙ 07/17/2020

Provably Consistent Partial-Label Learning

Partial-label learning (PLL) is a multi-class classification problem, wh...

5 Lei Feng, et al. ∙

research

∙ 07/05/2020

Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels

In weakly supervised learning, unbiased risk estimator(URE) is a powerfu...

23 Yu-Ting Chou, et al. ∙

research

∙ 06/14/2020

Parts-dependent Label Noise: Towards Instance-dependent Label Noise

Learning with the instance-dependent label noise is challenging, because...

0 Xiaobo Xia, et al. ∙

research

∙ 06/14/2020

Class2Simi: A New Perspective on Learning with Label Noise

Label noise is ubiquitous in the era of big data. Deep learning algorith...

0 Songhua Wu, et al. ∙

research

∙ 06/14/2020

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

The transition matrix, denoting the transition relationship from clean l...

0 Yu Yao, et al. ∙

Gang Niu

Featured Co-authors