Lecturer
- About
-
Biography
I am a Lecturer (US equivalent Assistant Professor) in the Natural and Computing School of the University of Aberdeen and head of the Multimodal Learning Lab. My research interests are machine learning, computer vision, and medical image analysis.
Before this, I was a Senior Research Fellow at the Computer Science Department of University College London, UK, till December 2022. I also worked as a Postdoctoral Research Associate at Imperial College London, UK, from December 2017 to July 2021. I obtained a PhD in Computer Science from Universite de Caen, France.
Potential PhD candidates: If you are interested in doing PhD at the University of Aberdeen, UK, please get in touch with me at binod.bhattarai@abdn.ac.uk
Selected Publications:
1. Poudel, P., Amgain, S., Shrestha, P., Shrestha, YR, Gyawali P., Bhattarai, B. CAR-MFL: Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalities MICCAI 2024
2. Bodur R., Bhattarai, B., Kim, T-K "Prompt Augmentation for Self-supervised Text-guided Image Manipulation" CVPR 2024
3. Bhattarai, B., Subedi, R., Gaire, RR, Vazquez, E., Stoyanov, D. "Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for 2D Surgical Image Semantic Segmentation", Medical Image Analysis (MedIA) 2023
4. Rau, A., Bhattarai, B., Agapito, L., & Stoyanov, D. "Bimodal camera pose prediction for endoscopy" Transactions on Medical Robotics and Bionics 2023
5. Caramalau, R. Bhattarai, B. and Kim, T-K "Sequential Graph Convolutional Network for Active Learning" CVPR 2021
6. Bhattarai, B. and Kim, T-K "Inducing Optimal Attributes Representations for Conditional GANs" ECCV 2020
7. Gecer, B. Bhattarai, B. Kittler, J. Kim, TK "Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model" ECCV 2018
For the details in the publication, visit https://scholar.google.com/citations?hl=en&user=PDEi58sAAAAJ
- Research
-
Research Areas
Accepting PhDs
I am currently accepting PhDs in Computing Science.
Please get in touch if you would like to discuss your research ideas further.
Computing Science
Accepting PhDsResearch Specialisms
- Computer Vision
- Machine Learning
- Biomedical Engineering
Our research specialisms are based on the Higher Education Classification of Subjects (HECoS) which is HESA open data, published under the Creative Commons Attribution 4.0 International licence.
- Teaching
-
Teaching Responsibilities
- Principles and Practice of Database Systems
- Foundations in Artificial Intelligence
- Publications
-
Page 1 of 1 Results 1 to 54 of 54
Task-Aware Active Learning for Endoscopic Polyp Segmentation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-73748-0_16
T2FNorm: Train-time Feature Normalization for OOD Detection in Image Classification
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] https://openaccess.thecvf.com/content/CVPR2024W/TCV2024/papers/Regmi_T2FNorm_Train-time_Feature_Normalization_for_OOD_Detection_in_Image_Classification_CVPRW_2024_paper.pdf
- [ONLINE] DOI: https://doi.org/10.1109/CVPRW63382.2024.00020
- [OPEN ACCESS] http://aura.abdn.ac.uk/bitstream/2164/24347/1/Regmi_etal_CVPR_T2FNorma_Train_Time_AAM.pdf
- [ONLINE] View publication in Scopus
IEdit: Localised Text-guided Image Editing with Weak Supervision
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/CVPRW63382.2024.00738
- [ONLINE] View publication in Scopus
ReweightOOD: Loss Reweighting for Distance-based OOD Detection
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/CVPRW63382.2024.00018
- [ONLINE] View publication in Scopus
Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise
Contributions to Conferences: PapersCAR-MFL: Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalities
Contributions to Conferences: PapersTE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer’s Disease Progression Analysis
Contributions to Conferences: PapersPrompt Augmentation for Self-supervised Text-guided Image Manipulation
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsTextAug: Test Time Text Augmentation for Multimodal Person Re-Identification
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/WACVW60836.2024.00040
- [ONLINE] View publication in Scopus
Placental vessel segmentation and registration in fetoscopy: Literature review and MICCAI FetReg2021 challenge findings
Medical Image Analysis, vol. 92, pp. 103066Contributions to Journals: Review articlesM-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-48593-0_4
- [ONLINE] View publication in Scopus
Neural Network Pruning for Real-Time Polyp Segmentation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-48593-0_22
- [ONLINE] View publication in Scopus
Dimension Mixer: A Generalized Method for Structured Sparsity in Deep Neural Networks
Working Papers: Preprint Papers- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2311.18735
Bimodal Camera Pose Prediction for Endoscopy
IEEE Transactions on Medical Robotics and Bionics, vol. 5, no. 4, pp. 978-989Contributions to Journals: Articles- [ONLINE] DOI: https://doi.org/10.1109/TMRB.2023.3320267
Task-Guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-44992-5_11
- [ONLINE] View publication in Scopus
- [ONLINE] AM at UCL Repository
A Client-Server Deep Federated Learning for Cross-Domain Surgical Image Segmentation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] https://arxiv.org/abs/2306.08720
- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-44992-5_3
- [ONLINE] View publication in Scopus
Improving Medical Image Classification in Noisy Labels Using only Self-supervised Pretraining
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-44992-5_8
- [ONLINE] View publication in Scopus
CholecTriplet2022: Show me a tool and tell me the triplet — An endoscopic vision challenge for surgical action triplet detection
Contributions to Journals: Short Survey- [ONLINE] DOI: https://doi.org/10.1016/j.media.2023.102888
- [ONLINE] View publication in Scopus
Preface DEMI 2023: Data Engineering in Medical Imaging
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-44992-5
- [ONLINE] View publication in Scopus
Why is the Winner the Best?
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/CVPR52729.2023.01911
- [ONLINE] View publication in Scopus
Task-Aware Active Learning for Endoscopic Polyp Segmentation
Working Papers: Preprint PapersJoint Training of Hierarchical GANs and Semantic Segmentation for Expression Translation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/ICASSP49357.2023.10097243
- [ONLINE] View publication in Scopus
Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation
Medical Image Analysis, vol. 85, 102747Contributions to Journals: ArticlesWhy is the winner the best?
Working Papers: Preprint Papers- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2303.17719
Dimension mixture model: Group Mixing of Input Dimensions for Efficient Function Approximation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] Stream of presentation
UNet-eVAE: Iterative Refinement Using VAE Embodied Learning for Endoscopic Image Segmentation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-21014-3_17
- [ONLINE] View publication in Scopus
Label Geometry Aware Discriminator for Conditional GAN
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/ICPR56361.2022.9956292
MoBYv2AL: Self-supervised Active Learning for Image Classification
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] https://bmvc2022.mpi-inf.mpg.de/674/
- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2301.01531
NepBERTa: Nepali Language Model Trained in a Large Corpus
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsGeneralized Product of Experts for Learning Multimodal Representations in Noisy Environments
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1145/3536221.3556596
Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics
Contributions to Conferences: Papers- [ONLINE] https://dynn-icml2022.github.io/posters/paper_6.pdf
- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2207.04467
SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency
The Computer Vision and Pattern Recognition ConferenceContributions to Conferences: Posters- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2111.09298
- [ONLINE] Conference website
Task-Aware Active Learning for Endoscopic Image Analysis
Working Papers: Working Papers- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2204.03440
A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation
Working Papers: Working Papers- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2112.04603
Sequential Graph Convolutional Network for Active Learning
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsBrand Label Albedo Extraction of eCommerce Products using Generative Adversarial Network
Contributions to Conferences: PapersFace Parsing from RGB and Depth Using Cross-Domain Mutual Learning
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/CVPRW53098.2021.00166
Input Invex Neural Network
Working Papers: Preprint Papers- [ONLINE] DOI: https://doi.org/10.48550/arXiv.2106.08748
3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/WACV48630.2021.00244
Visual Transformer for Task-aware Active Learning
Working Papers: Preprint Papers- [ONLINE] https://arxiv.org/abs/2106.03801
Active Learning for Bayesian 3D Hand Pose Estimation
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsInducing optimal attribute representations for conditional GANs
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-030-58571-6_5
Additive Angular Margin for Few Shot Learning to Classify Clinical Endoscopy Images
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-030-59861-7_50
MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsSampling Strategies for GAN Synthetic Data
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/ICASSP40776.2020.9054677
AugLabel: Exploiting Word Representations to Augment Labels for Face Attribute Classification
Working Papers: Preprint PapersSemi-supervised adversarial learning to generate photorealistic face images of new identities from 3D morphable model
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-030-01252-6_14
A joint learning approach for cross domain age estimation
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/ICASSP.2016.7472007
Cp-mtml: Coupled projection multi-task metric learning for large scale face retrieval
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsDeep fusion of visual signatures for client-server facial analysis
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] https://hal.science/hal-01390001v2
Some faces are more equal than others: Hierarchical organization for accurate and efficient large-scale identity-based face retrieval
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-319-16181-5_12
Puzzling face verification algorithms for privacy protection
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/WIFS.2014.7084305
Crosslingual Distributed Representations of Words
NIPS 2012 Workshop on Deep LearningContributions to Conferences: PostersInducing crosslingual distributed representations of words
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings