2 papers
cs.LG2022
SAGE: Saliency-Guided Mixup with Optimal Rearrangements
Avery Ma, Nikita Dvornik, Ran Zhang +3
Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation t…
cs.LG2022
Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations
Leila Pishdad, Ran Zhang, Konstantinos G. Derpanis +2
Probabilistic embeddings have proven useful for capturing polysemous word meanings, as well as ambiguity in image matching. In this paper, we study the advantages of probabilistic…