YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6

We develop an all-in-one computer vision tool-box named EasyCV to facilitate the use of various SOTA computer vision methods. Re-cently, we add YOLOX-PAI, an improved version of YOLOX, into EasyCV. We conduct ablation studies to investigate the influence of some detection methods on YOLOX. We also provide an easy use for PAI-Blade which is used to accelerate the inference process based on BladeDISC and TensorRT. Finally, we receive 42.8 mAP on COCO dateset within 1.0 ms on a single NVIDIA V100 GPU, which is a bit faster than YOLOv6. A simple but efficient predictor api is also designed in EasyCV to conduct end2end object detection. Codes and models are now available at: https://github. com/alibaba/EasyCV. 2022: Xinyi Zou, Ziheng Wu, Wenmeng Zhou, Jun Huang https://arxiv.org/pdf/2208.13040v2.pdf