3 citations · 6 across the 10 of their papers we have counts for
10 papers
SAGE: Saliency-Guided Contrastive Embeddings
Colton R. Crum, Christopher Sweet, Adam Czajka
Integrating human perceptual priors into the training of neural networks has been shown to raise model generalization, serve as an effective regularizer, and align models with huma…
Almost Right: Making First-Layer Kernels Nearly Orthogonal Improves Model Generalization
Colton R. Crum, Adam Czajka
Despite several algorithmic advances in the training of convolutional neural networks (CNNs) over the years, their generalization capabilities are still subpar across several perti…
Regulating Multifunctionality
Cary Coglianese, Colton R. Crum
Foundation models and generative artificial intelligence (AI) exacerbate a core regulatory challenge associated with AI: its heterogeneity. By their very nature, foundation models…
Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models
Colton R. Crum, Samuel Webster, Adam Czajka
Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presenta…
Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence
Cary Coglianese, Colton R. Crum
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 cal…
Iris Liveness Detection Competition (LivDet-Iris) -- The 2023 Edition
Patrick Tinsley, Sandip Purnapatra, Mahsa Mitcheff +18
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 inclu…
MENTOR: Human Perception-Guided Pretraining for Increased Generalization
Colton R. Crum, Adam Czajka
Leveraging human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the ac…
Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training
Colton R. Crum, Aidan Boyd, Kevin Bowyer +1
Machine learning models have shown increased accuracy in classification tasks when the training process incorporates human perceptual information. However, a challenge in training…
Generating Adversarial Samples in Mini-Batches May Be Detrimental To Adversarial Robustness
Timothy Redgrave, Colton Crum
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 incre…
Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models
Colton Crum, Patrick Tinsley, Aidan Boyd +5
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…