Zobrazeno 1 - 10
of 681
pro vyhledávání: '"Sinhamahapatra A"'
Multimodal foundation models aim to create a unified representation space that abstracts away from surface features like language syntax or modality differences. To investigate this, we study the internal representations of three recent models, analy
Externí odkaz:
http://arxiv.org/abs/2411.17666
Autor:
Sinhamahapatra, Poulami, Schwaiger, Franziska, Bose, Shirsha, Wang, Huiyu, Roscher, Karsten, Guennemann, Stephan
Detecting and localising unknown or Out-of-distribution (OOD) objects in any scene can be a challenging task in vision. Particularly, in safety-critical cases involving autonomous systems like automated vehicles or trains. Supervised anomaly segmenta
Externí odkaz:
http://arxiv.org/abs/2404.07664
Autor:
Sinhamahapatra, Poulami, Shit, Suprosanna, Sekuboyina, Anjany, Husseini, Malek, Schinz, David, Lenhart, Nicolas, Menze, Joern, Kirschke, Jan, Roscher, Karsten, Guennemann, Stephan
Publikováno v:
Machine.Learning.for.Biomedical.Imaging. 2 (2024)
Vertebral fracture grading classifies the severity of vertebral fractures, which is a challenging task in medical imaging and has recently attracted Deep Learning (DL) models. Only a few works attempted to make such models human-interpretable despite
Externí odkaz:
http://arxiv.org/abs/2404.02830
Publikováno v:
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, 878-887, 2023
Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However, instead of tryi
Externí odkaz:
http://arxiv.org/abs/2211.12173
Publikováno v:
SafeAI@AAAI (2022)
It is essential for safety-critical applications of deep neural networks to determine when new inputs are significantly different from the training distribution. In this paper, we explore this out-of-distribution (OOD) detection problem for image cla
Externí odkaz:
http://arxiv.org/abs/2203.08549
Autor:
Aniruddha Mondal, Muthuraja Velpandian, Himadri Tanaya Das, Apurba Sinhamahapatra, Suddhasatwa Basu, Mohd Afzal
Publikováno v:
Next Materials, Vol 3, Iss , Pp 100169- (2024)
The development of renewable energy technologies, such as fuel cells, electrolysersand metal-air batteries, relies heavily on the availability of highly efficient electrocatalysts for the anodic oxygen evolution reaction (OER). Defected ceria (D-CeO2
Externí odkaz:
https://doaj.org/article/22b1a3e5959c46a196ac372adaebfdcd
Publikováno v:
BMVC,2021
A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD) samples. In
Externí odkaz:
http://arxiv.org/abs/2107.08976
Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships remain a challe
Externí odkaz:
http://arxiv.org/abs/2107.05448
Autor:
Mondal, Aniruddha, Velpandian, Muthuraja, Das, Himadri Tanaya, Sinhamahapatra, Apurba, Basu, Suddhasatwa, Afzal, Mohd
Publikováno v:
In Next Materials April 2024 3
Publikováno v:
In Applied Clay Science 1 December 2023 245