Visual object recognition is impaired when stimuli are shown upside-down. This
phenomenon is known as the inversion effect, and a substantial body of evidence suggests …

Using register renaming and physical registers, modern microprocessors eliminate false
data dependences from reuse of the instruction set defined registers (logical registers). High …

Data augmentation improves the generalization power of deep learning models by
synthesizing more training samples. Sample-mixing is a popular data augmentation …

The objective of content-based image retrieval (CBIR) is to locate samples from a database
that are akin to a query, relying on the content embedded within the images. A contemporary …

We explore the impact of training with more diverse datasets, characterized by the number of
unique samples, on the performance of self-supervised learning (SSL) under a fixed …

Transfer learning could improve the robustness and generalization of the model, reducing
potential privacy and security risks. It operates by fine-tuning a pre-trained model on …

Due to large intra-class variation and inter-class ambiguity, fine-grained object recognition
has been a challenging task for decades. A good approach should be able to:(1) discover …

In this study, we propose a novel vision transformer neural tree decoder (ViT-NeT) that is
interpretable and highly accurate in terms of fine-grained visual categorization (FGVC). A …

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for
image representation learning. Various architectures, from vision transformers (ViTs) to …

Assessing distances between images and image datasets is a fundamental task in vision-
based research. It is a challenging open problem in the literature and despite the criticism it …