no code implementations • 10 Nov 2023 • Steven Korevaar, Ruwan Tennakoon, Ricky O'Brien, Dwarikanath Mahapatra, Alireza Bab-Hadiasha
This paper demonstrates that by using privileged information to predict the severity of intra-layer retinal fluid in optical coherence tomography scans, the classification accuracy of a deep learning model operating on out-of-distribution data improves from $0. 911$ to $0. 934$.
no code implementations • 12 Jul 2023 • WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, David Suter, Alireza Bab-Hadiashar
This approach is invariant to both affine shifts and changes in energy within a local feature patch and eliminates the need for commonly used non-linear activation functions.
no code implementations • 24 Oct 2022 • Shima Rashidi, Ruwan Tennakoon, Aref Miri Rekavandi, Papangkorn Jessadatavornwong, Amanda Freis, Garret Huff, Mark Easton, Adrian Mouritz, Reza Hoseinnezhad, Alireza Bab-Hadiashar
Distribution shift between train (source) and test (target) datasets is a common problem encountered in machine learning applications.
no code implementations • CVPR 2022 • WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, Alireza Bab-Hadiashar, David Suter
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains.
no code implementations • CVPR 2022 • Erchuan Zhang, David Suter, Ruwan Tennakoon, Tat-Jun Chin, Alireza Bab-Hadiashar, Giang Truong, Syed Zulqarnain Gilani
In particular, we study endowing the Boolean cube with the Bernoulli measure and performing biased (as opposed to uniform) sampling.
no code implementations • 21 Jun 2021 • Ayman Mukhaimar, Ruwan Tennakoon, Chow Yin Lai, Reza Hoseinnezhad, AlirezaBab-Hadiashar
The proposed pooling layer looks for data a mode/cluster using two methods, RANSAC, and histogram, as clusters are indicative of models.
no code implementations • 15 Jun 2021 • WeiQin Chuah, Ruwan Tennakoon, Alireza Bab-Hadiashar, David Suter
We provide evidence that demonstrates that learning of features in the synthetic domain by a stereo matching network is heavily influenced by two "shortcuts" presented in the synthetic data: (1) identical local statistics (RGB colour features) between matching pixels in the synthetic stereo images and (2) lack of realism in synthetic textures on 3D objects simulated in game engines.
1 code implementation • CVPR 2021 • Ruwan Tennakoon, David Suter, Erchuan Zhang, Tat-Jun Chin, Alireza Bab-Hadiashar
Consensus maximisation (MaxCon), which is widely used for robust fitting in computer vision, aims to find the largest subset of data that fits the model within some tolerance level.
no code implementations • 14 Oct 2020 • Joshua Thorpe, Ruwan Tennakoon, Alireza Bab-Hadiashar
In this paper we propose a single-stage graph neural network that can robustly perform rotation averaging in the presence of noise and outliers.
no code implementations • 10 Sep 2020 • WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, Alireza Bab-Hadiashar, David Suter
Consequently, the learning algorithms often produce unreliable depth estimates of foreground objects, particularly at large distances~($>50$m).
no code implementations • 2 Sep 2020 • Ayman Mukhaimar, Ruwan Tennakoon, Chow Yin Lai, Reza Hoseinnezhad, Alireza Bab-Hadiashar
In this paper, we present a robust spherical harmonics approach for the classification of point cloud-based objects.
no code implementations • 11 May 2020 • David Suter, Ruwan Tennakoon, Erchuan Zhang, Tat-Jun Chin, Alireza Bab-Hadiashar
This paper outlines connections between Monotone Boolean Functions, LP-Type problems and the Maximum Consensus Problem.
1 code implementation • 26 May 2017 • Ruwan Tennakoon, Alireza Sadri, Reza Hoseinnezhad, Alireza Bab-Hadiashar
In this paper, we propose an effective sampling method to obtain a highly accurate approximation of the full graph required to solve multi-structural model fitting problems in computer vision.
no code implementations • 20 Apr 2016 • Tharindu Rathnayake, Reza Hoseinnezhad, Ruwan Tennakoon, Alireza Bab-Hadiashar
This paper presents a track-before-detect labeled multi-Bernoulli filter tailored for industrial mobile platform safety applications.