A modified geometric transformation and mean-based class filtering in data augmentation pipelines, paired with an offline interpolation-specific pipeline, yields performance gains on medical image segmentation datasets by avoiding nearest-neighbor label and detail issues.
Selected Evaluation Metrics To evaluate the quality of predictions made by CNN architectures under various interpolation settings , Accuracy (Eq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Nearest Neighbor Interpolation in Data Augmentation
A modified geometric transformation and mean-based class filtering in data augmentation pipelines, paired with an offline interpolation-specific pipeline, yields performance gains on medical image segmentation datasets by avoiding nearest-neighbor label and detail issues.