My current research focuses on developing more efficient techniques for self-supervised representation learning from videos and images, parameter efficient adaptation of pre-trained models, generative AI, and low-level vision applications such as image super resolution, image segmentation, and change detection.
Embedded Files
Computer Vision Research
Computer Vision Research
Mixed Barlow Twins: Guarding Barlow Twins Against Overfitting with Mixed Samples 💥
Mixed Barlow Twins: Guarding Barlow Twins Against Overfitting with Mixed Samples 💥
Wele Gedara Chaminda Bandara, Celso M. De Melo, Vishal M. Patel
Mixed Barlow Twins aims to improve sample interaction during Barlow Twins training via linearly interpolated samples.Pre-training with this regularization effectively mitigates feature overfitting and further enhances the downstream performance on CIFAR-10, CIFAR-100, TinyImageNet, STL-10, and ImageNet datasets.
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling (FG'24)
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling (FG'24)
Oral Presentation (top 10% of accepted papers)
Wele Gedara Chaminda Bandara, Vishal M. Patel
Attention Prompt Tuning (APT) is a computationally efficient variant of prompt tun- ing for video-based applications such as action recognition.
CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models (CVPR'24)
CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models (CVPR'24)
Y. Ranasinghe, N. G. Nair, Wele Gedara Chaminda Bandara, Vishal M. Patel
We propose using conditional diffusion models to predict density maps, as diffusion models are known to model complex distributions well and show high fidelity to training data during crowd-density map generation.
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders (CVPR'23)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders (CVPR'23)
Wele Gedara Chaminda Bandara, Naman Patel, Ali Gholami, Mehdi Nikkhah, Motilal Agrawal, Vishal M. Patel
We propose AdaMAE, a novel, adaptive, and end-to-end trainable token sampling strategy for MAEs that takes into account the spatiotemporal properties of all input tokens to sample fewer but informative tokens.
Unite and Conquer: Cross Dataset Multimodal Synthesis using Diffusion Models (CVPR'23)
Unite and Conquer: Cross Dataset Multimodal Synthesis using Diffusion Models (CVPR'23)
Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, Vishal M. Patel
Our method can unite multiple diffusion models trained on multiple sub-tasks and conquer the combined task through our proposed sampling strategy.
DDPM-CD: Remote Sensing Change Detection using Denoising Diffusion Probabilistic Models (WACV'25)
DDPM-CD: Remote Sensing Change Detection using Denoising Diffusion Probabilistic Models (WACV'25)
Wele Gedara Chaminda Bandara, Nithin Gopalakrishnan Nair, Vishal M. Patel
We propose a novel way to learn the representations from off-the-shelf, unlabeled remote sensing images available by various Earth observation programs through the diffusion process.
Metric-CD: Deep Metric Learning for Unsupervised Remote Sensing Change Detection (WACV'25)
Metric-CD: Deep Metric Learning for Unsupervised Remote Sensing Change Detection (WACV'25)
Wele Gedara Chaminda Bandara, Vishal M. Patel
We propose an unsupervised change detection method based on deep metric learning.
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening (CVPR'22)
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening (CVPR'22)
Wele Gedara Chaminda Bandara, Vishal M. Patel
We propose a novel transformer network called HyperTransformer for HS pansharpening which achieves significant improvements over SOTA approaches. To the best of our knowledge, we are one of the first to introduce fusion transformer architecture for HS pansharpening.
Orientation-guided Graph Convolutional Network for Bone Surface Segmentation (MICCAI'22)
Orientation-guided Graph Convolutional Network for Bone Surface Segmentation (MICCAI'22)
Aimon Rahman, Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Ilker Hacihaliloglu, Vishal M Patel
We propose an orientation-guided graph convolutional network to improve connectivity while segmenting the bone surface.
ChangeFormer: A Transformer-Based Siamese Network for Change Detection (IGARSS'22)
ChangeFormer: A Transformer-Based Siamese Network for Change Detection (IGARSS'22)
Wele Gedara Chaminda Bandara, Vishal M. Patel
We presents a transformer-based Siamese network architecture for Change Detection (CD) from a pair of co-registered remote sensing images. The proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.
SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving (ICRA'22)
SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving (ICRA'22)
Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel
We propose a Spatial and Interaction Space Graph Reasoning (SPIN) module which when plugged into a ConvNet performs reasoning over graphs constructed on spatial and interaction spaces projected from the feature maps.
🎖️
Finalists of ICRA'22 Outstanding Automation Paper Award!
Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction (IEEE-TGRS)
Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction (IEEE-TGRS)
Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel
We proposed a novel approach for HS pansharpening, which mainly consists of three steps: (1) Upsampling the LR-HSI via DIP, (2) Predicting the residual image via over-complete HyperKite, and (3) Obtaining the final fused HSI by summation.
Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images (Under review)
Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images (Under review)
Wele Gedara Chaminda Bandara, Vishal M. Patel
We propose a semi-supervised CD paradigm based on consistency regularization. The proposed approach can effectively leverage the information from freely-available, unlabeled, multi-temporal, remote-sensing images to enhance the CD performance.
Transformer-based SAR Image Despeckling (IGARSS'22)
Transformer-based SAR Image Despeckling (IGARSS'22)
Malsha V. Perera, Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel
We propose a despeckling network comprises of a transformer-based encoder which allows the network to learn global dependencies between different image regions - aiding in better despeckling.
Multispectral & Hyperspectral Image Processing (no longer continuing)
Multispectral & Hyperspectral Image Processing (no longer continuing)
Validation of multispectral imaging for the detection of selected adulterants in turmeric samples
Journal of Food Engineering
Validation of multispectral imaging for the detection of selected adulterants in turmeric samples
Journal of Food Engineering
Wele Gedara Chaminda Bandara, G W K Prabhath, D W S C B Dissanayake, Vijitha R Herath, G M R I Godaliyadda, M P B Ekanayake, D Demini, Terrence Madhujith
We proposed a multispectral imaging system for detecting the percentage of the common adulterant; tartrazine colored rice flour found in turmeric powder.
Electrical Power Systems Research (no longer continuing)
Electrical Power Systems Research (no longer continuing)
Coordinated photovoltaic re-phasing: A novel method to maximize renewable energy integration in low voltage networks by mitigating network unbalances
Applied Energy
Coordinated photovoltaic re-phasing: A novel method to maximize renewable energy integration in low voltage networks by mitigating network unbalances
Applied Energy
W G Chaminda Bandara, G.M.R.I.Godaliyadda, M.P.B.Ekanayake, J.B.Ekanayake
We proposed a novel method is proposed to mitigate voltage unbalance in LV distribution grids by optimally re-phasing grid-connected rooftop PV systems.
🎖️
President's Award for Scientific Publications, 2020!
A complete state estimation algorithm for a three-phase four-wire low voltage distribution system with high penetration of solar PV
International Journal of Electrical Power & Energy Systems
A complete state estimation algorithm for a three-phase four-wire low voltage distribution system with high penetration of solar PV
International Journal of Electrical Power & Energy Systems
Wele Gedara Chaminda Bandara, Dilini Almeida, Roshan Indika Godaliyadda, Mervyn Parakrama Ekanayake, Janaka Ekanayake
We proposed a novel approach to estimate the complete state estimation of Low-Voltage Distribution Grids (LVDGs).
A Sensitivity Matrix Approach Using Two-Stage Optimization for Voltage Regulation of LV Networks with High PV Penetration Energies
A Sensitivity Matrix Approach Using Two-Stage Optimization for Voltage Regulation of LV Networks with High PV Penetration Energies
A.S. Jameel Hassan, Umar Marikkar, G.W. Kasun Prabhath, Aranee Balachandran, W.G. Chaminda Bandara, Parakrama B. Ekanayake, Roshan I. Godaliyadda, Janaka B. Ekanayake
Reactive Power Compensation for Voltage Violations in Distribution Network
Conference on Industrial and Information Systems (ICIIS)
Reactive Power Compensation for Voltage Violations in Distribution Network
Conference on Industrial and Information Systems (ICIIS)
Aranee Balachandran, G. W. K. Prabhath, W. G. Chaminda Bandara, G. M. R. I. Godaliyadda, M. P. B. Ekanayake, J. B. Ekanayake
Page updated
Google Sites
Report abuse