Resisting Large Data Variations via Introspective Transformation Network
WACV, pp. 3069-3078, 2020.
Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. Data variations in this paper include but not limited to unseen affine transformations and warping in the training data. One standard strategy to overcome this problem is to apply data augmentat...More
Full Text (Upload PDF)
PPT (Upload PPT)