no code implementations • 16 Mar 2024 • Mariia Khan, Yue Qiu, Yuren Cong, Jumana Abu-Khalaf, David Suter, Bodo Rosenhahn
The foundational Segment Anything Model (SAM) is designed for promptable multi-class multi-instance segmentation but tends to output part or sub-part masks in the "everything" mode for various real-world applications.
no code implementations • 10 Sep 2023 • Muraleekrishna Gopinathan, Jumana Abu-Khalaf, David Suter, Sidike Paheding, Nathir A. Rawashdeh
We show that local-global planning based on locality knowledge and predicting the indoor layout allows the agent to efficiently select the appropriate action.
1 code implementation • 22 Jul 2023 • Afsah Saleem, Zaid Ilyas, David Suter, Ghulam Mubashar Hassan, Siobhan Reid, John T. Schousboe, Richard Prince, William D. Leslie, Joshua R. Lewis, Syed Zulqarnain Gilani
We develop a Dual-encoder Contrastive Ordinal Learning (DCOL) framework that learns the contrastive ordinal representation at global and local levels to improve the feature separability and class diversity in latent space among the AAC-24 genera.
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 • 21 Feb 2022 • Giang Truong, Huu Le, Alvaro Parra, Syed Zulqarnain Gilani, Syed M. S. Islam, David Suter
The volume of data to handle, and still elusive need to have the registration occur fully reliably and fully automatically, mean there is a need to innovate further.
1 code implementation • CVPR 2022 • Anh-Dzung Doan, Michele Sasdelli, David Suter, Tat-Jun Chin
While our usage of quantum computing does not surmount the fundamental intractability of robust fitting, by providing error bounds our algorithm is a practical improvement over randomised heuristics.
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 • CVPR 2021 • Giang Truong, Huu Le, David Suter, Erchuan Zhang, Syed Zulqarnain Gilani
In this paper, we introduce a novel unsupervised learning framework that learns to directly solve robust model fitting.
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.
1 code implementation • 5 Mar 2021 • Giang Truong, Huu Le, David Suter, Erchuan Zhang, Syed Zulqarnain Gilani
In this paper, we introduce a novel unsupervised learning framework that learns to directly solve robust model fitting.
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 • 12 Jun 2020 • Tat-Jun Chin, David Suter, Shin-Fang Chng, James Quach
Many computer vision applications need to recover structure from imperfect measurements of the real world.
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.
no code implementations • 14 Feb 2020 • Haosheng Chen, David Suter, Qiangqiang Wu, Hanzi Wang
We feed the sequence of TSLTD frames to a novel Retinal Motion Regression Network (RMRNet) to perform an end-to-end 5-DoF object motion regression.
no code implementations • 13 Feb 2020 • Shuyuan Lin, Guobao Xiao, Yan Yan, David Suter, Hanzi Wang
Recently, some hypergraph-based methods have been proposed to deal with the problem of model fitting in computer vision, mainly due to the superior capability of hypergraph to represent the complex relationship between data points.
1 code implementation • ECCV 2018 • Zhipeng Cai, Tat-Jun Chin, Huu Le, David Suter
In this paper, we propose an efficient deterministic optimization algorithm for consensus maximization.
no code implementations • 3 May 2018 • Guobao Xiao, Hanzi Wang, Yan Yan, David Suter
Specifically, SDF includes three main parts: a deterministic sampling algorithm, a model hypothesis updating strategy and a novel model selection algorithm.
no code implementations • 4 Feb 2018 • Hanzi Wang, Guobao Xiao, Yan Yan, David Suter
We cast the task of geometric model fitting as a representative mode-seeking problem on hypergraphs.
1 code implementation • 27 Oct 2017 • Huu Le, Tat-Jun Chin, Anders Eriksson, Thanh-Toan Do, David Suter
Further, our approach is naturally applicable to estimation problems with geometric residuals
no code implementations • ICCV 2017 • Qianggong Zhang, Tat-Jun Chin, David Suter
Relative to the random sampling heuristic, our algorithm not only guarantees deterministic convergence to a local minimum, it typically achieves higher quality solutions in similar runtimes.
no code implementations • CVPR 2017 • Huu Le, Tat-Jun Chin, David Suter
Our method is based on a formulating the problem with linear complementarity constraints, then defining a penalized version which is provably equivalent to the original problem.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence 2016 • Pulak Purkait, Tat-Jun Chin, Hanno Ackermann, David Suter
The extension of conventional clustering to hypergraph clustering, which involves higher order similarities instead of pairwise similarities, is increasingly gaining attention in computer vision.
no code implementations • 20 Jul 2016 • Guobao Xiao, Hanzi Wang, Yan Yan, David Suter
The feature appearances are beneficial to reduce the computational complexity for deterministic fitting methods.
no code implementations • 11 Jul 2016 • Guobao Xiao, Hanzi Wang, Taotao Lai, David Suter
The hypergraph, with large and "data-determined" degrees of hyperedges, can express the complex relationships between model hypotheses and data points.
no code implementations • CVPR 2016 • Huu Le, Tat-Jun Chin, David Suter
Deformations of surfaces with the same intrinsic shape can often be described accurately by a conformal model.
no code implementations • ICCV 2015 • Hanzi Wang, Guobao Xiao, Yan Yan, David Suter
In addition to the mode seeking algorithm, MSH includes a similarity measure between vertices on the hypergraph and a weight-aware sampling technique.
no code implementations • 24 Mar 2016 • Yan Yan, Hanzi Wang, David Suter
In this paper, we propose an effective feature extraction algorithm, called Multi-Subregion based Correlation Filter Bank (MS-CFB), for robust face recognition.
no code implementations • CVPR 2015 • Tat-Jun Chin, Pulak Purkait, Anders Eriksson, David Suter
We aim to change this state of affairs by proposing a very efficient algorithm for global maximisation of consensus.
no code implementations • CVPR 2014 • Alvaro Parra Bustos, Tat-Jun Chin, David Suter
In this work, assuming that the translation parameters are known, we focus on constructing a fast rotation search algorithm.
1 code implementation • CVPR 2014 • Guosheng Lin, Chunhua Shen, Qinfeng Shi, Anton Van Den Hengel, David Suter
Here we propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data.
no code implementations • 23 Nov 2013 • Guosheng Lin, Chunhua Shen, Anton Van Den Hengel, David Suter
Different from most existing multi-class boosting methods, which use the same set of weak learners for all the classes, we train class specified weak learners (i. e., each class has a different set of weak learners).
no code implementations • 7 Sep 2013 • Guosheng Lin, Chunhua Shen, David Suter, Anton Van Den Hengel
This framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
no code implementations • CVPR 2013 • Julio Zaragoza, Tat-Jun Chin, Michael S. Brown, David Suter
We investigate projective estimation under model inadequacies, i. e., when the underpinning assumptions of the projective model are not fully satisfied by the data.
no code implementations • NeurIPS 2011 • Trung T. Pham, Tat-Jun Chin, Jin Yu, David Suter
Multi-structure model fitting has traditionally taken a two-stage approach: First, sample a (large) number of model hypotheses, then select the subset of hypotheses that optimise a joint fitting and model selection criterion.
no code implementations • NeurIPS 2009 • Tat-Jun Chin, Hanzi Wang, David Suter
The kernel permits the application of well-established statistical learning methods for effective outlier rejection, automatic recovery of the number of motions and accurate segmentation of the point trajectories.