Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Anatomy of a failure: When, how, and why deep vision fails in scientific domains
Ji-Hun Oh, Dou Hoon Kwark, Kianoush Falahkheirkhah +4
Mirroring its ubiquity in popular media and all human activities, the use of deep learning (DL) is rapidly growing in scientific imaging modalities. However, unlike everyday RGB pi…
cs.CV2025
Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification
Haowen Wang, Guowei Zhang, Xiang Zhang +4
In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to en…
cs.CV2025
Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score Fusion
Xiyue Zhu, Dou Hoon Kwark, Ruike Zhu +6
In volume-to-volume translations in medical images, existing models often struggle to capture the inherent volumetric distribution using 3D voxelspace representations, due to high…