Search Results for author: Pradeep Natarajan

Found 5 papers, 0 papers with code

Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models

no code implementations4 Sep 2021 Rakesh Chada, Pradeep Natarajan, Darshan Fofadiya, Prathap Ramachandra

We tested our approach for detecting misclassifications from one domain that accounts for <0. 5% of the traffic in a large-scale conversational AI system.

Named Entity Recognition Natural Language Understanding

FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models

no code implementations4 Sep 2021 Rakesh Chada, Pradeep Natarajan

On the multilingual TydiQA benchmark, our model outperforms the XLM-Roberta-large by an absolute margin of upto 40 F1 points and an average of 33 F1 points in a few-shot setting (<= 64 training examples).

Few-Shot Learning Question Answering

Style-Aware Normalized Loss for Improving Arbitrary Style Transfer

no code implementations CVPR 2021 Jiaxin Cheng, Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Prem Natarajan

Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST).

Style Transfer

Class-agnostic Object Detection

no code implementations28 Nov 2020 Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Premkumar Natarajan

Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions.

Object Detection Visual Grounding

Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts

no code implementations CVPR 2014 Shuang Wu, Sravanthi Bondugula, Florian Luisier, Xiaodan Zhuang, Pradeep Natarajan

Current state-of-the-art systems for visual content analysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples.

Event Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.