Search Results for author: Dilip K. Prasad

Found 23 papers, 6 papers with code

pNNCLR: Stochastic Pseudo Neighborhoods for Contrastive Learning based Unsupervised Representation Learning Problems

no code implementations14 Aug 2023 Momojit Biswas, Himanshu Buckchash, Dilip K. Prasad

Nearest neighbor (NN) sampling provides more semantic variations than pre-defined transformations for self-supervised learning (SSL) based image recognition problems.

Contrastive Learning Representation Learning +1

Latent Graph Attention for Enhanced Spatial Context

no code implementations9 Jul 2023 Ayush Singh, Yash Bhambhu, Himanshu Buckchash, Deepak K. Gupta, Dilip K. Prasad

In this paper, we present Latent Graph Attention (LGA) a computationally inexpensive (linear to the number of nodes) and stable, modular framework for incorporating the global context in the existing architectures, especially empowering small-scale architectures to give performance closer to large size architectures, thus making the light-weight architectures more useful for edge devices with lower compute power and lower energy needs.

Graph Attention Image Restoration +3

Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts

1 code implementation9 Mar 2023 Rohit Agarwal, Deepak Gupta, Alexander Horsch, Dilip K. Prasad

Many real-world applications based on online learning produce streaming data that is haphazard in nature, i. e., contains missing features, features becoming obsolete in time, the appearance of new features at later points in time and a lack of clarity on the total number of input features.


MABNet: Master Assistant Buddy Network with Hybrid Learning for Image Retrieval

1 code implementation6 Mar 2023 Rohit Agarwal, Gyanendra Das, Saksham Aggarwal, Alexander Horsch, Dilip K. Prasad

We present a novel Master Assistant Buddy Network (MABNet) for image retrieval which incorporates both learning mechanisms.

Image Retrieval Retrieval

Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective

1 code implementation3 Mar 2023 Animesh Gupta, Irtiza Hasan, Dilip K. Prasad, Deepak K. Gupta

We further show that when no pretraining is done or when the pretrained transformer models are used with non-natural images (e. g. medical data), CNNs tend to generalize better than transformers at even very small coreset sizes.

Benchmarking Image Classification +1

MiShape: 3D Shape Modelling of Mitochondria in Microscopy

no code implementations2 Mar 2023 Abhinanda R. Punnakkal, Suyog S Jadhav, Alexander Horsch, Krishna Agarwal, Dilip K. Prasad

Fluorescence microscopy is a quintessential tool for observing cells and understanding the underlying mechanisms of life-sustaining processes of all living organisms.

3D Shape Reconstruction

Patch Gradient Descent: Training Neural Networks on Very Large Images

no code implementations31 Jan 2023 Deepak K. Gupta, Gowreesh Mago, Arnav Chavan, Dilip K. Prasad

Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints.

On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?

1 code implementation24 Nov 2022 Saksham Aggarwal, Taneesh Gupta, Pawan Kumar Sahu, Arnav Chavan, Rishabh Tiwari, Dilip K. Prasad, Deepak K. Gupta

A comparison between SOTA trackers using CNNs, transformers as well as the combination of the two is presented to study their stability at various compression ratios.

Network Pruning Object Tracking

Partial Binarization of Neural Networks for Budget-Aware Efficient Learning

no code implementations12 Nov 2022 Udbhav Bamba, Neeraj Anand, Saksham Aggarwal, Dilip K. Prasad, Deepak K. Gupta

To address this issue, partial binarization techniques have been developed, but a systematic approach to mixing binary and full-precision parameters in a single network is still lacking.

Binarization Neural Network Compression +1

UltraMNIST Classification: A Benchmark to Train CNNs for Very Large Images

no code implementations25 Jun 2022 Deepak K. Gupta, Udbhav Bamba, Abhishek Thakur, Akash Gupta, Suraj Sharan, Ertugrul Demir, Dilip K. Prasad

Based on the outlined issues, we introduce a novel research problem of training CNN models for very large images, and present 'UltraMNIST dataset', a simple yet representative benchmark dataset for this task.

Semantic correspondence

Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering

no code implementations13 Nov 2021 Zicheng Liu, Mayank Roy, Dilip K. Prasad, Krishna Agarwal

Solving electromagnetic inverse scattering problems (ISPs) is challenging due to the intrinsic nonlinearity, ill-posedness, and expensive computational cost.

Simulation-supervised deep learning for analysing organelles states and behaviour in living cells

no code implementations26 Aug 2020 Arif Ahmed Sekh, Ida S. Opstad, Rohit Agarwal, Asa Birna Birgisdottir, Truls Myrmel, Balpreet Singh Ahluwalia, Krishna Agarwal, Dilip K. Prasad

Performing artificial intelligence (AI) tasks such as segmentation, tracking, and analytics of small sub-cellular structures such as mitochondria in microscopy videos of living cells is a prime example.

Multi-class Classification Segmentation

Neural network based country wise risk prediction of COVID-19

no code implementations31 Mar 2020 Ratnabali Pal, Arif Ahmed Sekh, Samarjit Kar, Dilip K. Prasad

Artificial intelligence (AI) driven methods can be useful to predict the parameters, risks, and effects of such an epidemic.

Bayesian Optimization

TMAV: Temporal Motionless Analysis of Video using CNN in MPSoC

no code implementations15 Feb 2019 Somdip Dey, Amit K. Singh, Dilip K. Prasad, Klaus D. McDonald-Maier

In our proposed methodology, called IRON-MAN (Integrated Rational prediction and Motionless ANalysis), we utilize Bayesian update on top of the individual image frame analysis in the videos and this has resulted in highly accurate prediction of Temporal Motionless Analysis of the Videos (TMAV) for most of the chosen test cases.


Can We Automate Diagrammatic Reasoning?

no code implementations13 Feb 2019 Sk. Arif Ahmed, Debi Prosad Dogra, Samarjit Kar, Partha Pratim Roy, Dilip K. Prasad

Preliminary results indicate that the domain is highly related to computer vision and pattern recognition research with several challenging avenues.

Visual Reasoning

Are object detection assessment criteria ready for maritime computer vision?

no code implementations12 Sep 2018 Dilip K. Prasad, Huixu Dong, Deepu Rajan, Chai Quek

However, the conventional assessment metrics suitable for usual object detection are deficient in the maritime setting.

object-detection Object Detection

Raw-to-Raw: Mapping between Image Sensor Color Responses

no code implementations CVPR 2014 Rang Nguyen, Dilip K. Prasad, Michael S. Brown

We show that this approach achieves state-of-the-art results on a range of consumer cameras and images of arbitrary scenes and illuminations.

Geometric primitive feature extraction - concepts, algorithms, and applications

no code implementations16 May 2013 Dilip K. Prasad

Three specific problems related to this topic have been studied, viz., polygonal approximation of digital curves, tangent estimation of digital curves, and ellipse fitting anddetection from digital curves.

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