About

Rahul Deora is a highly skilled Machine Learning Researcher with a strong background in mathematics, statistics and software engineering. He has over 4 years of relevant experience in the field and has worked on numerous machine learning and computer vision projects in research and production settings. Currently working as a Research Engineer at Fynd, Rahul is responsible for leading the machine learning, deep learning and computer vision research required for various tasks such as foreground identification and transparency prediction (Image Matting), object detection and tracking for retail store video analytics platform Fynd Trak, and implementing various metric learning approaches for visual recommendation search engine Fynd Now. He is also a core team member and principal researcher for EraseBG, a completely automated background removal service that is completely free even for high resolution images. Rahul has built a robust solution from scratch that can handle a huge variety of cases and took the solution to production level. Rahul has a strong online presence and has published two research papers in the field of machine learning and computer vision. His first publication, AlphaNet: An Attention Guided Deep Network for Automatic Image Matting, was published in IEEE and has also been featured in Arvix Pre-print. His second paper, Salient Image Matting, is currently in peer-review and has also been featured in Arvix Pre-print. Rahul has also created a small collection of blogs on his personal website and has a YouTube channel where he shares his knowledge and insights on machine learning and computer vision. Rahul has previously worked as a Research Intern at Indian Institute of Technology, Bombay, where he worked on tumor segmentation from multimodal MRI data and implemented representation learning models for automated feature extraction in tabular datasets. He has also worked as a Computer Vision and Machine Learning Intern at Orbo, where he automated image beautification and color corruption resolution. Rahul holds a Bachelor's degree in Mathematics and Statistics from Mithibai College and has also completed a Data Analyst Nanodegree from Udacity and a Full Stack Data Science Engineering course from GreyAtom. He has a strong tech stack that includes ML, Research Scientist, Computer Vision, Deep Learning, Object detection, Object Detection, Search, AI, and Dice loss. Rahul is currently looking for new opportunities in the field of computer vision and machine learning.