Search Results - "Aich, Shubhra"
-
1
Multi-Scale Weight Sharing Network for Image Recognition
Published in Pattern recognition letters (01-03-2020)“…•We explore the idea of weight sharing over multiple scales in convolutional networks.•We evaluate on two of the largest image recognition datasets (ImageNet…”
Get full text
Journal Article -
2
Leaf Counting with Deep Convolutional and Deconvolutional Networks
Published in 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) (01-10-2017)“…In this paper, we investigate the problem of counting rosette leaves from an RGB image, an important task in plant phenotyping. We propose a data-driven…”
Get full text
Conference Proceeding -
3
Domain Adaptation in LiDAR Semantic Segmentation via Hybrid Learning with Alternating Skip Connections
Published in 2023 IEEE Intelligent Vehicles Symposium (IV) (04-06-2023)“…In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled…”
Get full text
Conference Proceeding -
4
Probabilistic contour mapping using oriented gradient features and SVM-bagging
Published in 2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) (01-01-2015)“…In this paper, we propose a supervised approach to find out the probabilistic mapping of semantic contours in color images. We prepare a new color image…”
Get full text
Conference Proceeding -
5
Semantic Binary Segmentation Using Convolutional Networks without Decoders
Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2018)“…In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation. Our D2S model is comprised of a…”
Get full text
Conference Proceeding -
6
Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images
Published 28-05-2018“…In this paper, we explore the problem of training one-look regression models for counting objects in datasets comprising a small number of high-resolution,…”
Get full text
Journal Article -
7
Improving Object Counting with Heatmap Regulation
Published 14-03-2018“…In this paper, we propose a simple and effective way to improve one-look regression models for object counting from images. We use class activation map…”
Get full text
Journal Article -
8
Leaf Counting with Deep Convolutional and Deconvolutional Networks
Published 24-08-2017“…In this paper, we investigate the problem of counting rosette leaves from an RGB image, an important task in plant phenotyping. We propose a data-driven…”
Get full text
Journal Article -
9
Bidirectional Attention Network for Monocular Depth Estimation
Published in 2021 IEEE International Conference on Robotics and Automation (ICRA) (30-05-2021)“…In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation…”
Get full text
Conference Proceeding -
10
FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis
Published 13-10-2024“…The advancement in deep implicit modeling and articulated models has significantly enhanced the process of digitizing human figures in 3D from just a single…”
Get full text
Journal Article -
11
Deep Bayesian Future Fusion for Self-Supervised, High-Resolution, Off-Road Mapping
Published 18-03-2024“…High-speed off-road navigation requires long-range, high-resolution maps to enable robots to safely navigate over different surfaces while avoiding dangerous…”
Get full text
Journal Article -
12
Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters
Published in 2022 International Conference on Robotics and Automation (ICRA) (23-05-2022)“…In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant…”
Get full text
Conference Proceeding -
13
Using Large Text-to-Image Models with Structured Prompts for Skin Disease Identification: A Case Study
Published 17-01-2023“…This paper investigates the potential usage of large text-to-image (LTI) models for the automated diagnosis of a few skin conditions with rarity or a serious…”
Get full text
Journal Article -
14
PIAug -- Physics Informed Augmentation for Learning Vehicle Dynamics for Off-Road Navigation
Published 01-11-2023“…Modeling the precise dynamics of off-road vehicles is a complex yet essential task due to the challenging terrain they encounter and the need for optimal…”
Get full text
Journal Article -
15
Using Large Text To Image Models with Structured Prompts for Skin Disease Identification: A Case Study
Published in 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) (02-10-2023)“…This paper investigates the potential usage of large text-to-image (LTI) models for the automated diagnosis of a few skin conditions with rarity or a severe…”
Get full text
Conference Proceeding -
16
DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning
Published in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) (01-03-2018)“…In this paper, we investigate estimating emergence and biomass traits from color images and elevation maps of wheat field plots. We employ a state-of-the-art…”
Get full text
Conference Proceeding -
17
Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learning
Published 14-01-2022“…In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled…”
Get full text
Journal Article -
18
Multi-Scale Weight Sharing Network for Image Recognition
Published 08-01-2020“…In this paper, we explore the idea of weight sharing over multiple scales in convolutional networks. Inspired by traditional computer vision approaches, we…”
Get full text
Journal Article -
19
RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving
Published 21-11-2019“…In this paper, we strive for solving the ambiguities arisen by the astoundingly high density of raw PseudoLiDAR for monocular 3D object detection for…”
Get full text
Journal Article -
20
Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters
Published 20-07-2021“…In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant…”
Get full text
Journal Article