1 code implementation • 14 May 2024 • Dasith de Silva Edirimuni, Xuequan Lu, Gang Li, Lei Wei, Antonio Robles-Kelly, Hongdong Li
Point cloud filtering is a fundamental 3D vision task, which aims to remove noise while recovering the underlying clean surfaces.
no code implementations • 6 May 2023 • Weijia Wang, Xuequan Lu, Di Shao, Xiao Liu, Richard Dazeley, Antonio Robles-Kelly, Wei Pan
Existing normal estimation methods for point clouds are often less robust to severe noise and complex geometric structures.
no code implementations • 25 Apr 2023 • Tariq M. Khan, Syed S. Naqvi, Antonio Robles-Kelly, Imran Razzak
Timely and affordable computer-aided diagnosis of retinal diseases is pivotal in precluding blindness.
1 code implementation • CVPR 2023 • Dasith de Silva Edirimuni, Xuequan Lu, Zhiwen Shao, Gang Li, Antonio Robles-Kelly, Ying He
Consequently, a fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising.
no code implementations • 21 Feb 2023 • Matheus Moraes Hammes, Antonio Robles-Kelly
In the last two decades, the combination of machine learning and quantum computing has been an ever-growing topic of interest but, to this date, the limitations of quantum computing hardware have somewhat restricted the use of complex multi-qubit operations for machine learning.
1 code implementation • 18 Nov 2022 • Salma Gonzalez-Sabbagh, Antonio Robles-Kelly, Shang Gao
Our Dual Generator Dewatering cGAN (DGD-cGAN) removes the haze and colour cast induced by the water column and restores the true colours of underwater scenes whereby the effects of various attenuation and scattering phenomena that occur in underwater images are tackled by the two generators.
no code implementations • 15 Oct 2022 • Tariq M. Khan, Muhammad Arsalan, Antonio Robles-Kelly, Erik Meijering
Image segmentation is an important task in medical imaging.
no code implementations • 14 Oct 2022 • Tariq M. Khan, Syed S. Naqvi, Antonio Robles-Kelly, Erik Meijering
Compression of convolutional neural network models has recently been dominated by pruning approaches.
no code implementations • 5 Oct 2022 • Yang Yi, Xuequan Lu, Shang Gao, Antonio Robles-Kelly, Yuejie Zhang
Three new graph datasets are constructed based on ModelNet40, ModelNet10 and ShapeNet Part datasets.
no code implementations • 13 Sep 2022 • Khondaker Tasrif Noor, Antonio Robles-Kelly, Brano Kusy
Our ML-CapsNet predicts multiple image classes based on a hierarchical class-label tree structure.
1 code implementation • 14 Aug 2022 • Dasith de Silva Edirimuni, Xuequan Lu, Gang Li, Antonio Robles-Kelly
Existing methods usually perform normal estimation and filtering separately and often show sensitivity to noise and/or inability to preserve sharp geometric features such as corners and edges.
no code implementations • 27 May 2022 • Antonio Robles-Kelly, Asef Nazari
In this paper, we incorporate the Barzilai-Borwein step size into gradient descent methods used to train deep networks.
no code implementations • 21 Dec 2021 • Tariq M Khan, Antonio Robles-Kelly, Syed S. Naqvi
Over recent years, increasingly complex approaches based on sophisticated convolutional neural network architectures have been slowly pushing performance on well-established benchmark datasets.
no code implementations • 20 Oct 2021 • Weijia Wang, Xuequan Lu, Dasith de Silva Edirimuni, Xiao Liu, Antonio Robles-Kelly
It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector.
no code implementations • 12 Oct 2021 • Akib Mashrur, Wei Luo, Nayyar A. Zaidi, Antonio Robles-Kelly
Deep neural networks tend to underestimate uncertainty and produce overly confident predictions.
no code implementations • 23 Sep 2020 • Tariq M. Khan, Antonio Robles-Kelly
In this paper, we present a gradient-free approach for training multi-layered neural networks based upon quantum perceptrons.
no code implementations • 14 Aug 2020 • Shashank Gupta, Antonio Robles-Kelly, Mohamed Reda Bouadjenek
Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output.
no code implementations • 11 Jul 2020 • Dongbo Zhang, Zheng Fang, Xuequan Lu, Hong Qin, Antonio Robles-Kelly, Chao Zhang, Ying He
3D human segmentation has seen noticeable progress in re-cent years.
no code implementations • 22 Apr 2020 • Jingfeng Zhang, Cheng Li, Antonio Robles-Kelly, Mohan Kankanhalli
When the federated learning is adopted among competitive agents with siloed datasets, agents are self-interested and participate only if they are fairly rewarded.
no code implementations • 26 Feb 2020 • Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Antonio Robles-Kelly, Svetha Venkatesh
Again, it is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization process.
no code implementations • 5 Sep 2019 • Mehrdad Shoeiby, Lars Petersson, Mohammad Ali Armin, Sadegh Aliakbarian, Antonio Robles-Kelly
This paper introduces a novel method to simultaneously super-resolve and colour-predict images acquired by snapshot mosaic sensors.
no code implementations • 1 Apr 2019 • Mehrdad Shoeiby, Antonio Robles-Kelly, Ran Wei, Radu Timofte
This paper introduces a newly collected and novel dataset (StereoMSI) for example-based single and colour-guided spectral image super-resolution.
no code implementations • 15 Feb 2019 • Hao Zhu, Mantang Guo, Hongdong Li, Qing Wang, Antonio Robles-Kelly
We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.
no code implementations • 8 Dec 2017 • Junxuan Li, ShaoDi You, Antonio Robles-Kelly
Moreover, the non-linearity in deep nets, often achieved by a rectifier unit, is here cast as a convolution in the frequency domain.