Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Prabhushankar, Mohit"'
Autor:
Prabhushankar, Mohit, Kokilepersaud, Kiran, Quesada, Jorge, Yarici, Yavuz, Zhou, Chen, Alotaibi, Mohammad, AlRegib, Ghassan, Mustafa, Ahmad, Kumakov, Yusufjon
Crowdsourcing annotations has created a paradigm shift in the availability of labeled data for machine learning. Availability of large datasets has accelerated progress in common knowledge applications involving visual and language data. However, spe
Externí odkaz:
http://arxiv.org/abs/2408.11185
Autor:
AlRegib, Ghassan, Prabhushankar, Mohit, Kokilepersaud, Kiran, Chowdhury, Prithwijit, Fowler, Zoe, Corona, Stephanie Trejo, Thomaz, Lucas, Majumdar, Angshul
The VIP Cup offers a unique experience to undergraduates, allowing students to work together to solve challenging, real-world problems with video and image processing techniques. In this iteration of the VIP Cup, we challenged students to balance per
Externí odkaz:
http://arxiv.org/abs/2408.11170
In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed to enhance the robustness and accuracy of image classification models against viewpoint variations. Unlike traditional TTA methods that indiscriminately apply
Externí odkaz:
http://arxiv.org/abs/2406.08593
Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods ineffective in this context. In this paper, we introduce a novel method to
Externí odkaz:
http://arxiv.org/abs/2406.06930
Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner workings of these algorithms to elucidate their decision-making proce
Externí odkaz:
http://arxiv.org/abs/2406.07820
Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss
In this work, we propose a novel supervised contrastive loss that enables the integration of taxonomic hierarchy information during the representation learning process. A supervised contrastive loss operates by enforcing that images with the same cla
Externí odkaz:
http://arxiv.org/abs/2406.06848
This paper presents a discussion on data selection for deep learning in the field of seismic interpretation. In order to achieve a robust generalization to the target volume, it is crucial to identify the specific samples are the most informative to
Externí odkaz:
http://arxiv.org/abs/2406.05149
Autor:
Prabhushankar, Mohit, AlRegib, Ghassan
In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under perturbations to the input. Visu
Externí odkaz:
http://arxiv.org/abs/2406.00573
In this paper, we discuss feature engineering for single-pass uncertainty estimation. For accurate uncertainty estimates, neural networks must extract differences in the feature space that quantify uncertainty. This could be achieved by current singl
Externí odkaz:
http://arxiv.org/abs/2405.17494
Autor:
Prabhushankar, Mohit, AlRegib, Ghassan
The widespread adoption of deep neural networks in machine learning calls for an objective quantification of esoteric trust. In this paper we propose GradTrust, a classification trust measure for large-scale neural networks at inference. The proposed
Externí odkaz:
http://arxiv.org/abs/2405.13758