
Extended T: Learning with Mixed Closedset and Openset Noisy Labels
The label noise transition matrix T, reflecting the probabilities that t...
read it

A Survey of Labelnoise Representation Learning: Past, Present and Future
Classical machine learning implicitly assumes that labels of the trainin...
read it

Maximum Mean Discrepancy is Aware of Adversarial Attacks
The maximum mean discrepancy (MMD) test, as a representative twosample ...
read it

Experimental Quantum Generative Adversarial Networks for Image Generation
Quantum machine learning is expected to be one of the first practical ap...
read it

Quantum differentially private sparse regression learning
Differentially private (DP) learning, which aims to accurately extract p...
read it

Weakly Supervised Temporal Action Localization with SegmentLevel Labels
Temporal action localization presents a tradeoff between test performan...
read it

Partsdependent Label Noise: Towards Instancedependent Label Noise
Learning with the instancedependent label noise is challenging, because...
read it

Class2Simi: A New Perspective on Learning with Label Noise
Label noise is ubiquitous in the era of big data. Deep learning algorith...
read it

Dual T: Reducing Estimation Error for Transition Matrix in Labelnoise Learning
The transition matrix, denoting the transition relationship from clean l...
read it

Repulsive Mixture Models of Exponential Family PCA for Clustering
The mixture extension of exponential family principal component analysis...
read it

Quantum noise protects quantum classifiers against adversaries
Noise in quantum information processing is often viewed as a disruptive ...
read it

MultiClass Classification from NoisySimilarityLabeled Data
A similarity label indicates whether two instances belong to the same cl...
read it

Towards Mixture Proportion Estimation without Irreducibility
Mixture proportion estimation (MPE) is a fundamental problem of practica...
read it

Confidence Scores Make Instancedependent Labelnoise Learning Possible
Learning with noisy labels has drawn a lot of attention. In this area, m...
read it

A Shape Transformationbased Dataset Augmentation Framework for Pedestrian Detection
Deep learningbased computer vision is usually datahungry. Many researc...
read it

Continuous Dropout
Dropout has been proven to be an effective algorithm for training robust...
read it

Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
Deep neural networks (DNNs) are incredibly brittle due to adversarial ex...
read it

Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
The digital retina in smart cities is to select what the City Eye tells ...
read it

A Quantuminspired Algorithm for General Minimum Conical Hull Problems
A wide range of fundamental machine learning tasks that are addressed by...
read it

Truncated Cauchy Nonnegative Matrix Factorization
Nonnegative matrix factorization (NMF) minimizes the Euclidean distance...
read it

Are Anchor Points Really Indispensable in LabelNoise Learning?
In labelnoise learning, noise transition matrix, denoting the probabili...
read it

Orthogonal Deep Neural Networks
In this paper, we introduce the algorithms of Orthogonal Deep Neural Net...
read it

DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs
Due to the high storage and search efficiency, hashing has become preval...
read it

dipIQ: Blind Image Quality Assessment by LearningtoRank Discriminable Image Pairs
Objective assessment of image quality is fundamentally important in many...
read it

Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
The goal of transfer learning is to improve the performance of target le...
read it

Adaptive Morphological Reconstruction for Seeded Image Segmentation
Morphological reconstruction (MR) is often employed by seeded image segm...
read it

MultiView Matrix Completion for MultiLabel Image Classification
There is growing interest in multilabel image classification due to its...
read it

DecompositionBased Transfer Distance Metric Learning for Image Classification
Distance metric learning (DML) is a critical factor for image analysis a...
read it

Fast Supervised Discrete Hashing
Learningbased hashing algorithms are "hot topics" because they can grea...
read it

Supervised Discrete Hashing with Relaxation
Datadependent hashing has recently attracted attention due to being abl...
read it

A Regularization Approach for InstanceBased Superset Label Learning
Different from the traditional supervised learning in which each trainin...
read it

On Better Exploring and Exploiting Task Relationships in MultiTask Learning: Joint Model and Feature Learning
Multitask learning (MTL) aims to learn multiple tasks simultaneously thr...
read it

GenerativeDiscriminative Complementary Learning
Majority of stateoftheart deep learning methods for vision applicatio...
read it

Why ResNet Works? Residuals Generalize
Residual connections significantly boost the performance of deep neural ...
read it

Robust Angular Local Descriptor Learning
In recent years, the learned local descriptors have outperformed handcra...
read it

An Optimal Transport View on Generalization
We derive upper bounds on the generalization error of learning algorithm...
read it

The Expressive Power of Parameterized Quantum Circuits
Parameterized quantum circuits (PQCs) have been broadly used as a hybrid...
read it

Implementable Quantum Classifier for Nonlinear Data
In this Letter, we propose a quantum machine learning scheme for the cla...
read it

InstanceDependent PU Learning by Bayesian Optimal Relabeling
When learning from positive and unlabelled data, it is a strong assumpti...
read it

Domain Generalization via Conditional Invariant Representation
Domain generalization aims to apply knowledge gained from multiple label...
read it

An InformationTheoretic View for Deep Learning
Deep learning has transformed the computer vision, natural language proc...
read it

On the Rates of Convergence from Surrogate Risk Minimizers to the Bayes Optimal Classifier
We study the rates of convergence from empirical surrogate risk minimize...
read it

Learning with Biased Complementary Labels
In this paper we study the classification problem in which we have acces...
read it

Learning with Bounded Instance and Labeldependent Label Noise
Instance and labeldependent label noise (ILN) is widely existed in rea...
read it

Transfer Learning with Label Noise
Transfer learning aims to improve learning in the target domain with lim...
read it

Algorithmic stability and hypothesis complexity
We introduce a notion of algorithmic stability of learning algorithms...
read it

Local Blur Mapping: Exploiting HighLevel Semantics by Deep Neural Networks
The human visual system excels at detecting local blur of visual images,...
read it

Elastic Net Hypergraph Learning for Image Clustering and Semisupervised Classification
Graph model is emerging as a very effective tool for learning the comple...
read it

DimensionalityDependent Generalization Bounds for kDimensional Coding Schemes
The kdimensional coding schemes refer to a collection of methods that a...
read it

Classification with Noisy Labels by Importance Reweighting
In this paper, we study a classification problem in which sample labels ...
read it
Tongliang Liu
is this you? claim profile
Lecturer in machine learning at the School of Information Technologies, The University of Sydney. He received the BEng degree in electronic engineering and information science from the University of Science and Technology of China, and the PhD degree from the University of Technology Sydney. From October 2015 to March 2016, he was a visiting PhD student with Barcelona Graduate School of Economics (Barcelona GSE) and the Department of Economics at Pompeu Fabra University, Spain.