Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Sagar, Abhinav"'
Autor:
Sagar, Abhinav, Gilukara, Sai Teja
Sampling-based path planning algorithms play an important role in autonomous robotics. 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
Externí odkaz:
http://arxiv.org/abs/2305.10442
Autor:
Sagar, Abhinav
Publikováno v:
Springer, Cham 2021
In this paper, we propose a novel network named Vision Transformer for Biomedical Image Segmentation (ViTBIS). Our network splits the input feature maps into three parts with $1\times 1$, $3\times 3$ and $5\times 5$ convolutions in both encoder and d
Externí odkaz:
http://arxiv.org/abs/2201.05920
Autor:
Sagar, Abhinav
In this paper, we present a new network named Attention Aware Network (AASeg) for real time semantic image segmentation. Our network incorporates spatial and channel information using Spatial Attention (SA) and Channel Attention (CA) modules respecti
Externí odkaz:
http://arxiv.org/abs/2108.04349
Autor:
Sagar, Abhinav
In this work, we address the problem of 3D object detection from point cloud data in real time. For autonomous vehicles to work, it is very important for the perception component to detect the real world objects with both high accuracy and fast infer
Externí odkaz:
http://arxiv.org/abs/2107.12137
Autor:
Sagar, Abhinav
Attention mechanism of late has been quite popular in the computer vision community. A lot of work has been done to improve the performance of the network, although almost always it results in increased computational complexity. In this paper, we pro
Externí odkaz:
http://arxiv.org/abs/2106.08382
Autor:
Sagar, Abhinav
Drug discovery using deep learning has attracted a lot of attention of late as it has obvious advantages like higher efficiency, less manual guessing and faster process time. In this paper, we present a novel neural network for generating small molec
Externí odkaz:
http://arxiv.org/abs/2009.12368
Autor:
Sagar, Abhinav
Depth estimation from monocular images is a challenging problem in computer vision. In this paper, we tackle this problem using a novel network architecture using multi scale feature fusion. Our network uses two different blocks, first which uses dif
Externí odkaz:
http://arxiv.org/abs/2009.09934
Autor:
Sagar, Abhinav
In this paper, we present a novel network for high resolution video generation. Our network uses ideas from Wasserstein GANs by enforcing k-Lipschitz constraint on the loss term and Conditional GANs using class labels for training and testing. We pre
Externí odkaz:
http://arxiv.org/abs/2008.09646
Autor:
Sagar, Abhinav
Bayesian neural networks perform variational inference over the weights however calculation of the posterior distribution remains a challenge. Our work builds on variational inference techniques for bayesian neural networks using the original Evidenc
Externí odkaz:
http://arxiv.org/abs/2008.07587
Autor:
Sagar, Abhinav
In this work, we present a novel neural network to generate high resolution images. We replace the decoder of VAE with a discriminator while using the encoder as it is. The encoder is fed data from a normal distribution while the generator is fed fro
Externí odkaz:
http://arxiv.org/abs/2008.10399