Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Mohit Prabhushankar"'
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 4, Pp 284-293 (2023)
In this work, we present a methodology to shape a fisheye-specific representation space that reflects the interaction between distortion and semantic context present in this data modality. Fisheye data has the wider field of view advantage over other
Externí odkaz:
https://doaj.org/article/ac37eed822dd490d84e2f0e84d523ed4
Publikováno v:
IEEE Access, Vol 11, Pp 32716-32732 (2023)
We analyze the data-dependent capacity of neural networks and assess anomalies in inputs from the perspective of networks during inference. The notion of data-dependent capacity allows for analyzing the knowledge base of a model populated by learned
Externí odkaz:
https://doaj.org/article/9c952f72e1e54e80bbff7293e7d6f2fc
Autor:
Mohit Prabhushankar, Ghassan AlRegib
Publikováno v:
Frontiers in Neuroscience, Vol 17 (2023)
This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task. This is done
Externí odkaz:
https://doaj.org/article/63acc43434bd41c2b7feb9b61a46ba2d
Autor:
Ghassan AlRegib, Mohit Prabhushankar
Publikováno v:
IEEE Signal Processing Magazine. 39:59-72
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74fa9c26a1a37789b92524d1f998d5de
https://doi.org/10.1109/msp.2022.3163871
https://doi.org/10.1109/msp.2022.3163871
Autor:
Kiran Kokilepersaud, Stephanie Trejo Corona, Mohit Prabhushankar, Ghassan AlRegib, Charles Wykoff
This paper presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety of labels for data that serve d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39d6c5d2c5ded9502efd6b1fd60d4990
http://arxiv.org/abs/2305.15154
http://arxiv.org/abs/2305.15154
This paper considers deep out-of-distribution active learning. In practice, fully trained neural networks interact randomly with out-of-distribution (OOD) inputs and map aberrant samples randomly within the model representation space. Since data repr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::30099adf32b5d0861d07e96aaa3994a3
http://arxiv.org/abs/2301.05106
http://arxiv.org/abs/2301.05106
Autor:
Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib, Stephanie Trejo Corona, Charles Wykoff
Publikováno v:
2022 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::608e47ea99cf8020c023c4d80a8e51d8
https://doi.org/10.1109/icip46576.2022.9897215
https://doi.org/10.1109/icip46576.2022.9897215
Publikováno v:
Second International Meeting for Applied Geoscience & Energy.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::559be0e56527f950990c1a906aebd04f
https://doi.org/10.1190/image2022-3745292.1
https://doi.org/10.1190/image2022-3745292.1
Autor:
Mohit Prabhushankar, Ghassan AlRegib
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Neural networks trained to classify images do so by identifying features that allow them to distinguish between classes. These sets of features are either causal or context dependent. Grad-CAM is a popular method of visualizing both sets of features.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a09b7c58d8fd168654b16b2a829c88d
https://doi.org/10.1109/icip42928.2021.9506393
https://doi.org/10.1109/icip42928.2021.9506393
Publikováno v:
ICIP
In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs that can significantly degrade the performance of machine learning algori
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c97cfce7e62e255c1d898e47d94858ad
http://arxiv.org/abs/2008.06094
http://arxiv.org/abs/2008.06094