Kevin Benham

Kevin Benham

Auto-generated profile, based on publicly available information

Kevin Benham

Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
KBKevin Benham
Kevin Benham
PLPhillip Lewis
Phillip Lewis
JRJoseph C. Richardson
Joseph C. Richardson
Implementing reliable few-shot capable classifiers and detectors in machine learning (ML) is no trivial task and often requires parsing a large set of hyperparameters & training routine choices to find the best fit. One such choice is the loss function itself. In this effort we study validation & test performance of paired neural network (PNN) architectures using contrastive, hard-triplet, and semihard-triplet losses. These are tested by training multiple models to perform one-shot target detection on a custom synthetic hyperspectral image (HSI) dataset with and without reflectance calibration. We find that no single loss function is superior across all data treatments and standard scoring metrics can even disagree among the loss function choice among differing train, validation, & test split choices. We additionally analyze differences in detection map quality for selected test examples illustrating that while most are useful, some models will have more intuitive detection thresholds. Our work suggests multiple loss functions should be considered each time a new dataset and task are encountered to train PNNs for HSI target detection. These findings indicate significant variability in one-shot target detection performance based on the combination of training loss and data treatment but suggest the semihard-triplet loss, combined with a relatively simple reflectance calibration of the imagery, tends to generalize best across the common set of target materials studied.

1 January 2026
Verified
Report
Open access
PDF file
KBKevin Andrew Benham
Kevin Andrew Benham
U(Usdoe National Nuclear Security Administration (Nnsa)
Usdoe National Nuclear Security Administration (Nnsa)
A(Albuquerque Sandia National Laboratories (Snl-Nm)
Albuquerque Sandia National Laboratories (Snl-Nm)
EDElihu Deneke
Elihu Deneke
NWNicholas Albert Wyatt Wright
Nicholas Albert Wyatt Wright
JVJohn David VanderLaan
John David VanderLaan
Assessing structural integrity of large underground tunnel facilities is often a time consuming and human-labor intensive task. Thus, research using various modes of sensing and automated detection of key structural components in mines is posed to aid in safety assessments and establishing overall structural health. We propose an approach utilizing off-the-shelf camera and lidar technology fixed to a custom sensing platform, image stitching techniques, fine-tuned object detection models, and spe

1 April 2025
Verified
Report
Closed access
A(Albuquerque Sandia National Laboratories (Snl-Nm)
Albuquerque Sandia National Laboratories (Snl-Nm)
KBKevin Benham
Kevin Benham
EDElihu Deneke
Elihu Deneke
NWNicholas Wright
Nicholas Wright
KMKathryn Mondragon
Kathryn Mondragon
JWJeremy Wright
Jeremy Wright