Zobrazeno 1 - 10
of 95
pro vyhledávání: '"Dabeer, P."'
Autor:
Kim, Youngeun, Fang, Jun, Zhang, Qin, Cai, Zhaowei, Shen, Yantao, Duggal, Rahul, Raychaudhuri, Dripta S., Tu, Zhuowen, Xing, Yifan, Dabeer, Onkar
The open world is inherently dynamic, characterized by ever-evolving concepts and distributions. Continual learning (CL) in this dynamic open-world environment presents a significant challenge in effectively generalizing to unseen test-time classes.
Externí odkaz:
http://arxiv.org/abs/2409.05312
Autor:
Jeong, Jongheon, Zou, Yang, Kim, Taewan, Zhang, Dongqing, Ravichandran, Avinash, Dabeer, Onkar
Visual anomaly classification and segmentation are vital for automating industrial quality inspection. The focus of prior research in the field has been on training custom models for each quality inspection task, which requires task-specific images a
Externí odkaz:
http://arxiv.org/abs/2303.14814
Autor:
Jain, Achin, Swaminathan, Gurumurthy, Favaro, Paolo, Yang, Hao, Ravichandran, Avinash, Harutyunyan, Hrayr, Achille, Alessandro, Dabeer, Onkar, Schiele, Bernt, Swaminathan, Ashwin, Soatto, Stefano
We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset (e.g., 5 sa
Externí odkaz:
http://arxiv.org/abs/2303.01598
Autor:
Jain, Achin, Lee, Kibok, Swaminathan, Gurumurthy, Yang, Hao, Schiele, Bernt, Ravichandran, Avinash, Dabeer, Onkar
Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated dense sce
Externí odkaz:
http://arxiv.org/abs/2209.05654
Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class an
Externí odkaz:
http://arxiv.org/abs/2207.14315
Autor:
Lee, Kibok, Yang, Hao, Chakraborty, Satyaki, Cai, Zhaowei, Swaminathan, Gurumurthy, Ravichandran, Avinash, Dabeer, Onkar
Most existing works on few-shot object detection (FSOD) focus on a setting where both pre-training and few-shot learning datasets are from a similar domain. However, few-shot algorithms are important in multiple domains; hence evaluation needs to ref
Externí odkaz:
http://arxiv.org/abs/2207.11169
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Aladel A, Verma AK, Dabeer S, Ahmad I, Alshahrani MY, AboHassan MS, Khan MI, Almutairi MG, Beg MMA
Publikováno v:
Diabetes, Metabolic Syndrome and Obesity, Vol Volume 15, Pp 2535-2543 (2022)
Alanoud Aladel,1,* Amit K Verma,2,* Sadaf Dabeer,3 Irfan Ahmad,4 Mohammad Y Alshahrani,4 Mohammad S AboHassan,4 Mohammad Idreesh Khan,5,* Malak Ghazi Almutairi,6 Mirza Masroor Ali Beg7,8 1Department of Community Health Sciences, College o
Externí odkaz:
https://doaj.org/article/618260e807f842f98f26a83687a72dce
Publikováno v:
Diabetes, Metabolic Syndrome and Obesity, Vol Volume 15, Pp 1011-1021 (2022)
Amit K Verma,1,2 Alanoud Aladel,3 Sadaf Dabeer,4 Irfan Ahmad,5 Mohammad Idreesh Khan,6 Malak Ghazi Almutairi,7 Alhanouf I Al-Harbi,8 Mirza Masroor Ali Beg9,10 1Department of Biotechnology, Jamia Millia Islamia University, New Delhi, India; 2Departmen
Externí odkaz:
https://doaj.org/article/c0ca427f2e56497db1c93f2874a5c792
Autor:
Dabeer, Onkar, Gowaikar, Radhika, Grzechnik, Slawomir K., Lakshman, Mythreya J., Reitmayr, Gerhard, Somasundaram, Kiran, Sukhavasi, Ravi Teja, Wu, Xinzhou
Autonomous vehicles rely on precise high definition (HD) 3d maps for navigation. This paper presents the mapping component of an end-to-end system for crowdsourcing precise 3d maps with semantically meaningful landmarks such as traffic signs (6 dof p
Externí odkaz:
http://arxiv.org/abs/1703.10193