no code implementations • 13 May 2023 • Abhinav Sagar, Sai Teja Gilukara
However, a common problem among the RRT-based algorithms is that the initial path generated is not optimal and the convergence is too slow to be used in real-world applications.
no code implementations • 15 Jan 2022 • Abhinav Sagar
Similarly, transformer blocks and multi scale architecture is used in decoder before being linearly projected to produce the output segmentation map.
no code implementations • 29 Sep 2021 • Abhinav Sagar
Physics Informed Neural Networks has been quite successful in modelling the complex nature of fluid flow.
no code implementations • 27 Jul 2021 • Abhinav Sagar
In this paper, we present a new network named Attention Aware Network (AASeg) for real time semantic image segmentation.
no code implementations • 26 Jul 2021 • Abhinav Sagar
In this work, we address the problem of 3D object detection from point cloud data in real time.
no code implementations • 13 Jun 2021 • Abhinav Sagar
Attention mechanism of late has been quite popular in the computer vision community.
no code implementations • 15 Sep 2020 • Abhinav Sagar
In this paper, we present a novel neural network for generating small molecules similar to the ones in the training set.
no code implementations • 11 Sep 2020 • Abhinav Sagar
Depth estimation from monocular images is a challenging problem in computer vision.
no code implementations • arXiv 2020 • Abhinav Sagar
In this paper, we present a novel network for high resolution video generation.
no code implementations • arXiv 2020 • Abhinav Sagar
In this work, we present a novel neural network to generate high resolution images.
no code implementations • 12 Aug 2020 • Abhinav Sagar
Our work builds on variational inference techniques for bayesian neural networks using the original Evidence Lower Bound.
1 code implementation • 12 Aug 2020 • Abhinav Sagar
Deep learning motivated by convolutional neural networks has been highly successful in a range of medical imaging problems like image classification, image segmentation, image synthesis etc.
no code implementations • 11 Jul 2020 • Abhinav Sagar
However dense crowd counting remains an open problem because of severe occlusion and perspective view in which people can be present at various sizes.
no code implementations • 30 Jun 2020 • Abhinav Sagar, RajKumar Soundrapandiyan
In this paper, we present a novel neural network using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation.
Ranked #68 on Semantic Segmentation on Cityscapes test
no code implementations • 4 Jun 2020 • Abhinav Sagar
This work extends the work done by others by deriving the variational inference models.
no code implementations • 14 May 2020 • Abhinav Sagar, Dheeba J
Our model achieves the best of results using ResNet50 with accuracy of 0. 982, precision of 0. 94, recall of 0. 94 and F1 score of 0. 94.
no code implementations • 14 May 2020 • Abhinav Sagar, Dheeba J
In this work, we address the problem of skin cancer classification using convolutional neural networks.
1 code implementation • 9 May 2020 • Abhinav Sagar
In this work, we address the problem of 3D object detection from point cloud data in real time.