5 citations · 5 across the 2 of their papers we have counts for
3 papers
cs.LG2026
Variance Fingerprints: Component-Wise Identification of Content Factors by Augmentation Design
D. Hudson Smith
Augmentation-based self-supervised learning can recover the content shared across views without separating its underlying factors into individual coordinates. We ask whether augmen…
cs.CV2026
Spatial Attention Noise Masking for Causally Sufficient Interpretability
Benjamin Formby, Kuang-Ching Wang, D Hudson Smith
We present a novel causal approach to interpretability for computer vision models that dynamically masks the input image prior to classification. The interpretability of deep learn…
cs.CV2023★ 5 cited
On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
D. Hudson Smith, John Paul Lineberger, George H. Baker
Many medical ultrasound video recognition tasks involve identifying key anatomical features regardless of when they appear in the video suggesting that modeling such tasks may not…