Abstract: A small target object refers to an object whose relative size of the bounding box is very small, usually the ratio of the width of the bounding box to the width and height of the original ...

Swin Transformer (the name Swin stands for S hifted win dow) is initially described in arxiv, which capably serves as a general-purpose backbone for computer vision. It is basically a hierarchical ...

Global context information is essential for the semantic segmentation of remote sensing (RS) images. However, most existing methods rely on a convolutional neural network (CNN), which is challenging ...

Hi! First of all, many thanks for your fantastic work. I've encountered a problem when optimizing (4-bit dynamic quantization models with PEFT/LoRA, e.g. qwen2.5 or qwen3) that I don't have when using ...