pranavsinghps1,Pranav Singh,github

DEDL Introduces novel Autoencoder post-processing for image segmentation which improves upon traditional segmentation architecture by 3% at no extra space and inference time. We also introduce data-efficient deep learning methods for medical image classification and segmentation which improves upon previous approaches by 26% and 5%. Arixv Paper , Papers with Code , Accepted at ECCV - Medical Computer Vision Workshop 2022
CASS is a novel resource-efficient self-supervised learning approach developed for medical image analysis which is computationally efficient and better performing than state-of-the-art self-supervised learning approaches. Arixv Paper , Papers with Code, Accepted at NeurIPS Self-Supervised Learning Theory & Practice Workshop 2022
My Implementation of Deepmind's BYOL Self-supervised technique for lightly-ai.
My Contribution for facebook research's VISSL Project, Implementation of Deepmind's BYOL Self-supervised technique can be found here - Single GPU Implementation and Updates.
CVPR 2021/FGVC8 (Fine-Grained Visual Categorization) Plant Pathology Challenge (Top 9%).
Co-authored a paper on “Melanoma Classification using efficient nets with multiple ensembles and patient-level data”, International Conference on Computational Intelligence - ICCI 2020, IIIT Pune.
Top 57% in Lyft's Motion Prediction for Autonomous Vehicles.
Top 43% in Google Research's Open Images Object Detection RVC 2020 edition.

Recommend Projects