Search Results for author: Subhradeep Kayal

Found 7 papers, 3 papers with code

Unsupervised Sentence-embeddings by Manifold Approximation and Projection

1 code implementation EACL 2021 Subhradeep Kayal

The concept of unsupervised universal sentence encoders has gained traction recently, wherein pre-trained models generate effective task-agnostic fixed-dimensional representations for phrases, sentences and paragraphs.

Sentence Embeddings Text Classification +1

Revisiting Edge Detection in Convolutional Neural Networks

no code implementations25 Dec 2020 Minh Le, Subhradeep Kayal

The ability to detect edges is a fundamental attribute necessary to truly capture visual concepts.

Edge Detection

Region-of-interest guided Supervoxel Inpainting for Self-supervision

1 code implementation26 Jun 2020 Subhradeep Kayal, Shuai Chen, Marleen de Bruijne

Self-supervised learning has proven to be invaluable in making best use of all of the available data in biomedical image segmentation.

Image Inpainting Self-Supervised Learning +1

Spectral Data Augmentation Techniques to quantify Lung Pathology from CT-images

no code implementations24 Apr 2020 Subhradeep Kayal, Florian Dubost, Harm A. W. M. Tiddens, Marleen de Bruijne

Data augmentation is of paramount importance in biomedical image processing tasks, characterized by inadequate amounts of labelled data, to best use all of the data that is present.

Data Augmentation Texture Classification

EigenSent: Spectral sentence embeddings using higher-order Dynamic Mode Decomposition

1 code implementation ACL 2019 Subhradeep Kayal, George Tsatsaronis

Distributed representation of words, or word embeddings, have motivated methods for calculating semantic representations of word sequences such as phrases, sentences and paragraphs.

Sentence Embeddings Word Embeddings

Tagging Funding Agencies and Grants in Scientific Articles using Sequential Learning Models

no code implementations WS 2017 Subhradeep Kayal, Zubair Afzal, George Tsatsaronis, Sophia Katrenko, Pascal Coupet, Marius Doornenbal, Michelle Gregory

In this paper we present a solution for tagging funding bodies and grants in scientific articles using a combination of trained sequential learning models, namely conditional random fields (CRF), hidden markov models (HMM) and maximum entropy models (MaxEnt), on a benchmark set created in-house.

Document Summarization Information Retrieval +2

Unsupervised Image Segmentation using the Deffuant-Weisbuch Model from Social Dynamics

no code implementations15 Apr 2016 Subhradeep Kayal

In this paper, a popular theoretical model with it's origins in statistical physics and social dynamics, known as the Deffuant-Weisbuch model, is applied to the image segmentation problem.

Semantic Segmentation Unsupervised Image Segmentation

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