All Outputs (25)

Exemplar-supported representation for effective class-incremental learning. (2020)
Journal Article
GUO, L., XIE, G., XU, X. and REN, J. 2020. Exemplar-supported representation for effective class-incremental learning. IEEE access [online], 8, pages 51276-51284. Available from: https://doi.org/10.1109/ACCESS.2020.2980386

Catastrophic forgetting is a key challenge for class-incremental learning with deep neural networks, where the performance decreases considerably while dealing with long sequences of new classes. To tackle this issue, in this paper, we propose a new... Read More about Exemplar-supported representation for effective class-incremental learning..

Weakly supervised conditional random fields model for semantic segmentation with image patches. (2020)
Journal Article
XU, X., XUE, Y., HAN, X., ZHANG, Z., XIE, J. and REN, J. 2020. Weakly supervised conditional random fields model for semantic segmentation with image patches. Applied sciences [online], 10(5), article 1679. Available from: https://doi.org/10.3390/app10051679

Image semantic segmentation (ISS) is used to segment an image into regions with differently labeled semantic category. Most of the existing ISS methods are based on fully supervised learning, which requires pixel-level labeling for training the model... Read More about Weakly supervised conditional random fields model for semantic segmentation with image patches..

Varietal classification of rice seeds using RGB and hyperspectral images. (2020)
Journal Article
FABIYI, S.D., VU, H., TACHTATZIS, C., MURRAY, P., HARLE, D., DAO, T.K., ANDONOVIC, I., REN, J. and MARSHALL, S. 2020. Varietal classification of rice seeds using RGB and hyperspectral images. IEEE access [online], 8, pages 22493-22505. Available from: https://doi.org/10.1109/ACCESS.2020.2969847

Inspection of rice seeds is a crucial task for plant nurseries and farmers since it ensures seed quality when growing seedlings. Conventionally, this process is performed by expert inspectors who manually screen large samples of rice seeds to identif... Read More about Varietal classification of rice seeds using RGB and hyperspectral images..

MIMN-DPP: maximum-information and minimum-noise determinantal point processes for unsupervised hyperspectral band selection. (2020)
Journal Article
CHEN, W., YANG, Z., REN, J., CAO, J., CAI, N., ZHAO, H. and YUEN, P. 2020. MIMN-DPP: maximum-information and minimum-noise determinantal point processes for unsupervised hyperspectral band selection. Pattern recognition [online], 102, article 107213. Available from: https://doi.org/10.1016/j.patcog.2020.107213

Band selection plays an important role in hyperspectral imaging for reducing the data and improving the efficiency of data acquisition and analysis whilst significantly lowering the cost of the imaging system. Without the category labels, it is chall... Read More about MIMN-DPP: maximum-information and minimum-noise determinantal point processes for unsupervised hyperspectral band selection..

Automatic extraction of water inundation areas using Sentinel-1 data for large plain areas. (2020)
Journal Article
HU, S., QIN, J., REN, J., ZHAO, H., REN, J., and HONG, H. 2020. Automatic extraction of water inundation areas using sentinel-1 data for large plain areas. Remote sensing [online], 12(2), article 243. Available from: https://doi.org/10.3390/rs12020243

Accurately quantifying water inundation dynamics in terms of both spatial distributions and temporal variability is essential for water resources management. Currently, the water map is usually derived from synthetic aperture radar (SAR) data with th... Read More about Automatic extraction of water inundation areas using Sentinel-1 data for large plain areas..