论文标题
将辅助的超级推理和小型对象检测进行微调
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection
论文作者
论文摘要
在现场遥远的小物体和对象的检测是监视应用中的一个主要挑战。这些对象由图像中的少量像素表示，并且缺乏足够的细节，因此使用常规检测器很难检测到它们。在这项工作中，提出了一个称为切片的超级推理（SAHI）的开源框架，该框架提供了一个通用切片的辅助推理和用于小对象检测的辅助推理和微调管道。该提出的技术是通用的，因为它可以在任何可用的对象检测器之上应用，而无需进行任何微调。实验评估，使用对象检测基准在Visdrone和Xview Aerial对象检测数据集上表明，FCO，VFNET和TOOD检测器分别将对象检测方法分别增加6.8％，5.1％和5.3％。此外，通过切片辅助微调，可以进一步提高检测准确性，从而导致累计增加12.7％，13.4％和14.5％的AP按照相同的顺序。拟议的技术已与DentectRon2，MMDetection和Yolov5模型集成在一起，并在https://github.com/obss/sahi.git上公开获得。
Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect using conventional detectors. In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection. The proposed technique is generic in the sense that it can be applied on top of any available object detector without any fine-tuning. Experimental evaluations, using object detection baselines on the Visdrone and xView aerial object detection datasets show that the proposed inference method can increase object detection AP by 6.8%, 5.1% and 5.3% for FCOS, VFNet and TOOD detectors, respectively. Moreover, the detection accuracy can be further increased with a slicing aided fine-tuning, resulting in a cumulative increase of 12.7%, 13.4% and 14.5% AP in the same order. Proposed technique has been integrated with Detectron2, MMDetection and YOLOv5 models and it is publicly available at https://github.com/obss/sahi.git .
