Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Crum, Colton"'
Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic samples. After
Externí odkaz:
http://arxiv.org/abs/2405.00650
Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence
Autor:
Coglianese, Cary, Crum, Colton R.
Fervent calls for more robust governance of the harms associated with artificial intelligence (AI) are leading to the adoption around the world of what regulatory scholars have called a management-based approach to regulation. Recent initiatives in t
Externí odkaz:
http://arxiv.org/abs/2402.08466
Autor:
Crum, Colton R., Czajka, Adam
Incorporating human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture) and ho
Externí odkaz:
http://arxiv.org/abs/2310.19545
Autor:
Tinsley, Patrick, Purnapatra, Sandip, Mitcheff, Mahsa, Boyd, Aidan, Crum, Colton, Bowyer, Kevin, Flynn, Patrick, Schuckers, Stephanie, Czajka, Adam, Fang, Meiling, Damer, Naser, Liu, Xingyu, Wang, Caiyong, Sun, Xianyun, Chang, Zhaohua, Li, Xinyue, Zhao, Guangzhe, Tapia, Juan, Busch, Christoph, Aravena, Carlos, Schulz, Daniel
This paper describes the results of the 2023 edition of the ''LivDet'' series of iris presentation attack detection (PAD) competitions. New elements in this fifth competition include (1) GAN-generated iris images as a category of presentation attack
Externí odkaz:
http://arxiv.org/abs/2310.04541
Machine learning models have shown increased accuracy in classification tasks when the training process incorporates human perceptual information. However, a challenge in training human-guided models is the cost associated with collecting image annot
Externí odkaz:
http://arxiv.org/abs/2306.05527
Autor:
Redgrave, Timothy, Crum, Colton
Neural networks have been proven to be both highly effective within computer vision, and highly vulnerable to adversarial attacks. Consequently, as the use of neural networks increases due to their unrivaled performance, so too does the threat posed
Externí odkaz:
http://arxiv.org/abs/2303.17720
Autor:
Crum, Colton, Tinsley, Patrick, Boyd, Aidan, Piland, Jacob, Sweet, Christopher, Kelley, Timothy, Bowyer, Kevin, Czajka, Adam
The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of critical impor
Externí odkaz:
http://arxiv.org/abs/2303.11969