research
∙
08/12/2023
Multi-Label Knowledge Distillation
Existing knowledge distillation methods typically work by imparting the ...
share
research
∙
07/21/2023
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images
Knowledge distillation aims to learn a lightweight student network from ...
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...
research
∙
06/20/2023
A Universal Unbiased Method for Classification from Aggregate Observations
In conventional supervised classification, true labels are required for ...
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...
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...
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...
research
∙
05/10/2023
Towards Effective Visual Representations for Partial-Label Learning
Under partial-label learning (PLL) where, for each training instance, on...
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...
research
∙
04/30/2023
Assessing Vulnerabilities of Adversarial Learning Algorithm through Poisoning Attacks
Adversarial training (AT) is a robust learning algorithm that can defend...
research
∙
12/08/2022
Logit Clipping for Robust Learning against Label Noise
In the presence of noisy labels, designing robust loss functions is crit...
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 ...
research
∙
10/05/2022
FedMT: Federated Learning with Mixed-type Labels
In federated learning (FL), classifiers (e.g., deep networks) are traine...
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...
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 ...
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...
research
∙
02/22/2022
On the Effectiveness of Adversarial Training against Backdoor Attacks
DNNs' demand for massive data forces practitioners to collect data from ...
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...
research
∙
01/22/2022
PiCO: Contrastive Label Disambiguation for Partial Label Learning
Partial label learning (PLL) is an important problem that allows each tr...
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 ...
research
∙
09/07/2021
Instance-dependent Label-noise Learning under a Structural Causal Model
Label noise will degenerate the performance of deep learning algorithms ...
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...
research
∙
06/30/2021
Local Reweighting for Adversarial Training
Instances-reweighted adversarial training (IRAT) can significantly boost...
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? ...
research
∙
06/15/2021
Probabilistic Margins for Instance Reweighting in Adversarial Training
Reweighting adversarial data during training has been recently shown to ...
research
∙
06/11/2021
Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted sign...
research
∙
06/11/2021
On the Robustness of Average Losses for Partial-Label Learning
Partial-label (PL) learning is a typical weakly supervised classificatio...
research
∙
06/09/2021
Reliable Adversarial Distillation with Unreliable Teachers
In ordinary distillation, student networks are trained with soft labels ...
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 ...
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...
research
∙
05/31/2021
NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?
Adversarial training (AT) based on minimax optimization is a popular lea...
research
∙
02/13/2021
Learning from Similarity-Confidence Data
Weakly supervised learning has drawn considerable attention recently to ...
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...
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 ...
research
∙
02/06/2021
Understanding the Interaction of Adversarial Training with Noisy Labels
Noisy labels (NL) and adversarial examples both undermine trained models...
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 ...
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...
research
∙
02/03/2021
Learning Diverse-Structured Networks for Adversarial Robustness
In adversarial training (AT), the main focus has been the objective and ...
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...
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...
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 ...
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...
research
∙
10/22/2020
Maximum Mean Discrepancy is Aware of Adversarial Attacks
The maximum mean discrepancy (MMD) test, as a representative two-sample ...
research
∙
10/05/2020
Pointwise Binary Classification with Pairwise Confidence Comparisons
Ordinary (pointwise) binary classification aims to learn a binary classi...
research
∙
10/05/2020
Geometry-aware Instance-reweighted Adversarial Training
In adversarial machine learning, there was a common belief that robustne...
research
∙
07/17/2020
Provably Consistent Partial-Label Learning
Partial-label learning (PLL) is a multi-class classification problem, wh...
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...
research
∙
06/14/2020
Parts-dependent Label Noise: Towards Instance-dependent Label Noise
Learning with the instance-dependent label noise is challenging, because...
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...
research
∙
06/14/2020