GitHub

Boltzmann Attention Sampling for Image Analysis with Small Objects

BoltzFormer is designed for text promptable segmentation, with superior performance for small objects. It performs Boltzmann sampling within the attention mechanism in the transformer, allowing the ...
GitHub

Lightweight Adaptive Feature Selection Network for Enhanced Small Object Detection in UAV Imagery

Official PyTorch implementation of LWSDet. [Lightweight Adaptive Feature Selection Network for Enhanced Small Object Detection in UAV Imagery] Jinxia Yu, Jie Wu, Yongli Tang Abstract To address the ...
IEEE

AUD-YOLO: A Lightweight Object Detection Algorithm Model Incorporating Dynamic Upsampling for Remote Sensing Images

Abstract: In the field of remote sensing image processing, remote sensing image object detection is a crucial undertaking. However, the existing object detection algorithms have a considerable number ...
Federal Register

Notice of Determinations; Culturally Significant Objects Being Imported for Exhibition-Determinations: “Carol Bove” Exhibition

This site displays a prototype of a “Web 2.0” version of the daily Federal Register. It is not an official legal edition of the Federal Register, and does not replace the official print version or the ...
IEEE

Physical Adversarial Background Patch Against Aerial Object Detection Based on Pareto Efficiency

Abstract: For adversarial attacks on aerial image object detection, some physical background attack methods have been proposed and demonstrated excellent performance. However, most of the methods ...