976 citations
- Commonwealth Scientific and Industrial Research OrganisationAU30 papers
- The University of SydneyAU16 papers
- UNSW SydneyAU8 papers
- Hong Kong University of Science and TechnologyHK3 papers
- Australian National UniversityAU2 papers
- Carnegie Mellon UniversityUS2 papers
- SupélecFR2 papers
- Universidad Nacional Autónoma de MéxicoMX2 papers
- Université de SherbrookeCA2 papers
- University of PittsburghUS2 papers
- University of South AustraliaAU2 papers
- Academia SinicaTW1 paper
41 papers
Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification
Cheng Deng, Yumeng Xue, Xianglong Liu +2
Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network…
Diversity, Productivity, and Growth of Open Source Developer Communities
Qingye Jiang, Young Choon Lee, Joseph G. Davis +1
The open source development model has become a paradigm shift from traditional in-house/closed-source software development model, with many successes. Traditionally, open source pr…
Metamorphic Moving Horizon Estimation
He Kong, Salah Sukkarieh
This paper considers a practical scenario where a classical estimation method might have already been implemented on a certain platform when one tries to apply more advanced techni…
Quantum Divide-and-Conquer Anchoring for Separable Non-negative Matrix Factorization
Yuxuan Du, Tongliang Liu, Yinan Li +2
It is NP-complete to find non-negative factors and with fixed rank from a non-negative matrix by minimizing . Although the separability assumptio…
Learning with Biased Complementary Labels
Xiyu Yu, Tongliang Liu, Mingming Gong +1
In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that o…
Transfer Learning with Label Noise
Xiyu Yu, Tongliang Liu, Mingming Gong +3
Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and t…