Abstract: Small object detection represents a pivotal sub-domain within the field of computer vision. Previous research aimed at enhancing detection accuracy has included augmenting the head layer, ...

Abstract: Feature representation is crucial for hyperspectral image (HSI) classification. However, existing convolutional neural network (CNN)-based methods are limited by the convolution kernel and ...

In this paper, we consider the strong instability of standing waves for the Hartree equation with a constant magnetic field.

CODA is a GPU kernel abstraction that expresses Transformer operators as GEMM-plus-epilogue programs, fusing normalization, activations, residual updates, and reductions into the GEMM output tile ...