858 citations
- The University of AdelaideAU53 papers
- The University of SydneyAU40 papers
- Australian National UniversityAU38 papers
- Queensland University of TechnologyAU28 papers
- Data61AU14 papers
- Monash UniversityAU10 papers
- University of Technology SydneyAU9 papers
- Commonwealth Scientific and Industrial Research OrganisationAU7 papers
- Northwestern Polytechnical UniversityCN7 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- The University of QueenslandAU4 papers
- Vision AustraliaAU4 papers
11 papers · 1 filter
Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique
Connor Malone, Stephen Hausler, Tobias Fischer +1
One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods…
ROSIA: Rotation-Search-Based Star Identification Algorithm
Chee-Kheng Chng, Alvaro Parra Bustos, Benjamin McCarthy +1
This paper presents a rotation-search-based approach for addressing the star identification (Star-ID) problem. The proposed algorithm, ROSIA, is a heuristics-free algorithm that se…
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
Chong Wang, Yuanhong Chen, Yuyuan Liu +6
State-of-the-art (SOTA) deep learning mammogram classifiers, trained with weakly-labelled images, often rely on global models that produce predictions with limited interpretability…
A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels
Emeson Santana, Gustavo Carneiro, Filipe R. Cordeiro
Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strateg…
CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification
Zhibin Liao, Kewen Liao, Haifeng Shen +6
Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems. A comm…
CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data
Ke Zhang, Jin Fan, Shaoli Huang +3
Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing correspon…