Deep Learning

HTML Atomic UI Elements Extraction from Hand-Drawn Website Images using Mask-RCNN and novel Multi-Pass Inference Technique

11$^{th}$ International Conference of the CLEF Association (CLEF 2020) - Thessaloniki, Greece

HTML UI element extraction

Extracted HTML UI elements from wireframe drawings of websites ideating novel multi-pass inference technique to boost recall. Achieved $3^{rd}$ rank in the hackathon.

Active Learning

Explored Active Learning with different querying strategies on CIFAR10 dataset and managed to achieve high accuracies with very limited training data

Implementation of live models on edge

Implemented and optimised multiple live models (eg. action recognition on something something dataset with over 200 classes) on edge devices (eg. Jetson TX2, Raspberry Pi)

Damaged Car Parts Segmentation for auto claims

Performed damaged car parts segmentation for automating auto claims with additional features like explainability and automated claim / damage report generation