26 citations · 31 across the 9 of their papers we have counts for
9 papers
Physics-Driven ML-Based Modelling for Correcting Inverse Estimation
Ruiyuan Kang, Tingting Mu, Panos Liatsis +1
When deploying machine learning estimators in science and engineering (SAE) domains, it is critical to avoid failed estimations that can have disastrous consequences, e.g., in aero…
Faster Riemannian Newton-type Optimization by Subsampling and Cubic Regularization
Yian Deng, Tingting Mu
This work is on constrained large-scale non-convex optimization where the constraint set implies a manifold structure. Solving such problems is important in a multitude of fundamen…
A Unified Theory of Diversity in Ensemble Learning
Danny Wood, Tingting Mu, Andrew Webb +3
We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios. This challenge has been referred to as the holy gra…
Improved Imaging by Invex Regularizers with Global Optima Guarantees
Samuel Pinilla, Tingting Mu, Neil Bourne +1
Image reconstruction enhanced by regularizers, e.g., to enforce sparsity, low rank or smoothness priors on images, has many successful applications in vision tasks such as computer…
Data-driven Approaches to Surrogate Machine Learning Model Development
H. Rhys Jones, Tingting Mu, Andrei C. Popescu +1
We demonstrate the adaption of three established methods to the field of surrogate machine learning model development. These methods are data augmentation, custom loss functions an…
Bias-Variance Decompositions for Margin Losses
Danny Wood, Tingting Mu, Gavin Brown
We introduce a novel bias-variance decomposition for a range of strictly convex margin losses, including the logistic loss (minimized by the classic LogitBoost algorithm), as well…
Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks
Maolin Li, Arvid Fahlström Myrman, Tingting Mu +1
When constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide…
On Class Imbalance and Background Filtering in Visual Relationship Detection
Alessio Sarullo, Tingting Mu
In this paper we investigate the problems of class imbalance and irrelevant relationships in Visual Relationship Detection (VRD). State-of-the-art deep VRD models still struggle to…
VommaNet: an End-to-End Network for Disparity Estimation from Reflective and Texture-less Light Field Images
Haoxin Ma, Haotian Li, Zhiwen Qian +2
The precise combination of image sensor and micro-lens array enables lenslet light field cameras to record both angular and spatial information of incoming light, therefore, one ca…