Easter2.0: Improving convolutional models for handwritten text recognition

1 code implementation • 30 May 2022 • Kartik Chaudhary, Raghav Bali

In addition to the Easter2. 0 architecture, we propose a simple and effective data augmentation technique 'Tiling and Corruption (TACO)' relevant for the task of HTR/OCR.

Data Augmentation Few-Shot Learning +3

EASTER: Efficient and Scalable Text Recognizer

no code implementations • 18 Aug 2020 • Kartik Chaudhary, Raghav Bali

In this paper, we present an Efficient And Scalable TExt Recognizer (EASTER) to perform optical character recognition on both machine printed and handwritten text.

Benchmarking Handwritten Text Recognition +2

An Interpretable Deep Learning System for Automatically Scoring Request for Proposals

no code implementations • 5 Aug 2020 • Subhadip Maji, Anudeep Srivatsav Appe, Raghav Bali, Veera Raghavendra Chikka, Arijit Ghosh Chowdhury, Vamsi M Bhandaru

We also qualitatively asses the impact of important phrases using human evaluators.

A Simple and Interpretable Predictive Model for Healthcare

no code implementations • 27 Jul 2020 • Subhadip Maji, Raghav Bali, Sree Harsha Ankem, Kishore V Ayyadevara

We push the capabilities of a tree based model and come up with a strong baseline for more sophisticated models.

Disease Prediction

Exclusion and Inclusion -- A model agnostic approach to feature importance in DNNs

1 code implementation • 13 Jul 2020 • Subhadip Maji, Arijit Ghosh Chowdhury, Raghav Bali, Vamsi M Bhandaru

Deep Neural Networks in NLP have enabled systems to learn complex non-linear relationships.

Feature Importance regression