Search Results for author: Ayan Das

Found 18 papers, 4 papers with code

BézierSketch: A generative model for scalable vector sketches

1 code implementation ECCV 2020 Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process.

Image Generation

Image generation with shortest path diffusion

1 code implementation1 Jun 2023 Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili, Da-Shan Shiu, Alberto Bernacchia

We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring.

Deblurring Image Generation

Score Normalization for a Faster Diffusion Exponential Integrator Sampler

1 code implementation31 Oct 2023 Guoxuan Xia, Duolikun Danier, Ayan Das, Stathi Fotiadis, Farhang Nabiei, Ushnish Sengupta, Alberto Bernacchia

As a simple fix, we propose to instead reparameterise the score (at inference) by dividing it by the average absolute value of previous score estimates at that time step collected from offline high NFE generations.

HMM-based Indic Handwritten Word Recognition using Zone Segmentation

no code implementations1 Aug 2017 Partha Pratim Roy, Ayan Kumar Bhunia, Ayan Das, Prasenjit Dey, Umapada Pal

To avoid character segmentation in such scripts, HMM-based sequence modeling has been used earlier in holistic way.

Segmentation

Distributed Weighted Parameter Averaging for SVM Training on Big Data

no code implementations30 Sep 2015 Ayan Das, Sourangshu Bhattacharya

Experimental results on a variety of toy and real world datasets show that our approach is significantly more accurate than parameter averaging for high number of partitions.

Development of a Bengali parser by cross-lingual transfer from Hindi

no code implementations WS 2016 Ayan Das, Agnivo Saha, Sudeshna Sarkar

A parser is trained and applied to the Hindi sentences of the parallel corpus and the parse trees are projected to construct probable parse trees of the corresponding Bengali sentences.

Chunking Cross-Lingual Transfer +1

Improving cross-lingual model transfer by chunking

no code implementations27 Feb 2020 Ayan Das, Sudeshna Sarkar

We present a shallow parser guided cross-lingual model transfer approach in order to address the syntactic differences between source and target languages more effectively.

Chunking Sentence

Cloud2Curve: Generation and Vectorization of Parametric Sketches

1 code implementation CVPR 2021 Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations.

Demographic noise can promote abrupt transitions in ecological systems

no code implementations29 Mar 2021 Sabiha Majumder, Ayan Das, Appilineni Kushal, Sumithra Sankaran, Vishwesha Guttal

In this paper, we show that demographic noise may, in fact, promote abrupt transitions in systems that would otherwise show continuous transitions.

SketchODE: Learning neural sketch representation in continuous time

no code implementations ICLR 2022 Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

Learning meaningful representations for chirographic drawing data such as sketches, handwriting, and flowcharts is a gateway for understanding and emulating human creative expression.

Data Augmentation

A little perturbation makes a difference: Treebank augmentation by perturbation improves transfer parsing

no code implementations ICON 2019 Ayan Das, Sudeshna Sarkar

We present an approach for cross-lingual transfer of dependency parser so that the parser trained on a single source language can more effectively cater to diverse target languages.

Cross-Lingual Transfer

A Graph Convolution Network-based System for Technical Domain Identification

no code implementations ICON 2020 Alapan Kuila, Ayan Das, Sudeshna Sarkar

This paper presents the IITKGP contribution at the Technical DOmain Identification (TechDOfication) shared task at ICON 2020.

Classification domain classification +2

ChiroDiff: Modelling chirographic data with Diffusion Models

no code implementations7 Apr 2023 Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

Such strictly-ordered discrete factorization however falls short of capturing key properties of chirographic data -- it fails to build holistic understanding of the temporal concept due to one-way visibility (causality).

Denoising

A study of the impact of generative AI-based data augmentation on software metadata classification

no code implementations14 Oct 2023 Tripti Kumari, Chakali Sai Charan, Ayan Das

This paper presents the system submitted by the team from IIT(ISM) Dhanbad in FIRE IRSE 2023 shared task 1 on the automatic usefulness prediction of code-comment pairs as well as the impact of Large Language Model(LLM) generated data on original base data towards an associated source code.

Data Augmentation Language Modelling +1

Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes

no code implementations7 Dec 2023 Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Ayan Kumar Bhunia, Yi-Zhe Song

In this paper, we democratise 3D content creation, enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills.

Position

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