no code implementations • 28 Mar 2024 • Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey
In the realm of computer vision, Neural Fields have gained prominence as a contemporary tool harnessing neural networks for signal representation.
no code implementations • 27 Mar 2024 • Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi
Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
1 code implementation • 29 Feb 2024 • Xianghui Yang, Yan Zuo, Sameera Ramasinghe, Loris Bazzani, Gil Avraham, Anton Van Den Hengel
Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images.
no code implementations • 8 Feb 2024 • Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey
Implicit Neural Representations (INRs) have gained popularity for encoding signals as compact, differentiable entities.
1 code implementation • 5 Oct 2023 • Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe, Ali Cheraghian, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
In knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models.
Ranked #1 on Classification on CIFAR-100
1 code implementation • 1 Sep 2023 • Jianqiao Zheng, Xueqian Li, Sameera Ramasinghe, Simon Lucey
End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment.
no code implementations • ICCV 2023 • Hemanth Saratchandran, Shin-Fang Chng, Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey
Coordinate networks are widely used in computer vision due to their ability to represent signals as compressed, continuous entities.
no code implementations • 10 Mar 2023 • Sameera Ramasinghe, Hemanth Saratchandran, Violetta Shevchenko, Simon Lucey
Modelling dynamical systems is an integral component for understanding the natural world.
no code implementations • 27 Feb 2023 • Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Anton Van Den Hengel
Reasoning the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem.
no code implementations • 17 Jun 2022 • Sameera Ramasinghe, Lachlan MacDonald, Moshiur Farazi, Hemanth Saratchandran, Simon Lucey
Characterizing the remarkable generalization properties of over-parameterized neural networks remains an open problem.
1 code implementation • 30 May 2022 • Townim Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman
Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training.
1 code implementation • 18 May 2022 • Jianqiao Zheng, Sameera Ramasinghe, Xueqian Li, Simon Lucey
It is well noted that coordinate-based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier features.
2 code implementations • 12 Apr 2022 • Shin-Fang Chng, Sameera Ramasinghe, Jamie Sherrah, Simon Lucey
Despite Neural Radiance Fields (NeRF) showing compelling results in photorealistic novel views synthesis of real-world scenes, most existing approaches require accurate prior camera poses.
no code implementations • 1 Feb 2022 • Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey
We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in computer vision for representing high-frequency signals.
no code implementations • 21 Dec 2021 • Sameera Ramasinghe, Simon Lucey
We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings.
1 code implementation • 30 Nov 2021 • Sameera Ramasinghe, Simon Lucey
Coordinate-MLPs are emerging as an effective tool for modeling multidimensional continuous signals, overcoming many drawbacks associated with discrete grid-based approximations.
1 code implementation • CVPR 2022 • Lachlan Ewen MacDonald, Sameera Ramasinghe, Simon Lucey
Our framework enables the implementation of group convolutions over any finite-dimensional Lie group.
1 code implementation • 6 Jul 2021 • Jianqiao Zheng, Sameera Ramasinghe, Simon Lucey
It is well noted that coordinate based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier features.
no code implementations • 6 Feb 2021 • Sameera Ramasinghe, Kasun Fernando, Salman Khan, Nick Barnes
Modeling real-world distributions can often be challenging due to sample data that are subjected to perturbations, e. g., instrumentation errors, or added random noise.
no code implementations • ICCV 2021 • Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe, Pengfei Fang, Christian Simon, Lars Petersson, Mehrtash Harandi
In this paper, we propose addressing this problem using a mixture of subspaces.
1 code implementation • NeurIPS 2021 • Sameera Ramasinghe, Moshiur Farazi, Salman Khan, Nick Barnes, Stephen Gould
Conditional GANs (cGAN), in their rudimentary form, suffer from critical drawbacks such as the lack of diversity in generated outputs and distortion between the latent and output manifolds.
no code implementations • ICLR 2021 • Sameera Ramasinghe, Kanchana Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould
Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings.
1 code implementation • 4 Dec 2019 • Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould
Point-clouds are a popular choice for vision and graphics tasks due to their accurate shape description and direct acquisition from range-scanners.
no code implementations • 30 Nov 2019 • Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould
In this work, we propose a novel `\emph{volumetric convolution}' operation that can effectively model and convolve arbitrary functions in $\mathbb{B}^3$.
no code implementations • 24 Aug 2019 • Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould
Existing networks directly learn feature representations on 3D point clouds for shape analysis.
no code implementations • ICLR 2019 • Sameera Ramasinghe, Salman Khan, Nick Barnes
Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks.
no code implementations • 16 Oct 2018 • Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
We propose three schemas for combining static and motion components: based on a variance ratio, principal components, and Cholesky decomposition.
no code implementations • 15 Oct 2018 • Sameera Ramasinghe, C. D. Athuralya, Salman Khan
Recently proposed Capsule Network is a brain inspired architecture that brings a new paradigm to deep learning by modelling input domain variations through vector based representations.