论文标题
Yowo-Plus：增量改进
YOWO-Plus: An Incremental Improvement
论文作者
论文摘要
在这份技术报告中，我们想向Yowo介绍我们的更新，这是一种实时的时空操作检测方法。我们进行了一堆小的设计更改，以使其变得更好。对于网络结构，我们使用了相同的官方实施的Yowo，包括3D-Resnext-101和Yolov2，但是我们使用了重新完成的Yolov2的预算重量，这比官方的Yolov2更好。我们还优化了Yowo中使用的标签分配。为了准确检测行动实例，我们将giou损失用于盒子回归。在我们的增量改进之后，Yowo在UCF101-24上实现了84.9 \％框架图和50.5 \％视频地图，显着高于官方Yowo。在AVA上，我们优化的Yowo用16帧获得20.6 \％框架图，也超过了官方的Yowo。使用32帧，我们的Yowo在RTX 3090 GPU上使用25 fps实现21.6帧地图。我们将优化的Yowo命名为Yowo-Plus。此外，我们用高效的3D-shuffleenet-V2替换3D-Resnext-101，以设计轻质动作检测器Yowo-Nano。 Yowo-nano在UCF101-24上实现81.0 \％框架图和49.7 \％视频框架图。它还可以在AVA上使用约90 fps实现18.4 \％框架图。据我们所知，Yowo-Nano是最先进的动作检测器。我们的代码可在https://github.com/yjh0410/pytorch_yowo上找到。
In this technical report, we would like to introduce our updates to YOWO, a real-time method for spatio-temporal action detection. We make a bunch of little design changes to make it better. For network structure, we use the same ones of official implemented YOWO, including 3D-ResNext-101 and YOLOv2, but we use a better pretrained weight of our reimplemented YOLOv2, which is better than the official YOLOv2. We also optimize the label assignment used in YOWO. To accurately detection action instances, we deploy GIoU loss for box regression. After our incremental improvement, YOWO achieves 84.9\% frame mAP and 50.5\% video mAP on the UCF101-24, significantly higher than the official YOWO. On the AVA, our optimized YOWO achieves 20.6\% frame mAP with 16 frames, also exceeding the official YOWO. With 32 frames, our YOWO achieves 21.6 frame mAP with 25 FPS on an RTX 3090 GPU. We name the optimized YOWO as YOWO-Plus. Moreover, we replace the 3D-ResNext-101 with the efficient 3D-ShuffleNet-v2 to design a lightweight action detector, YOWO-Nano. YOWO-Nano achieves 81.0 \% frame mAP and 49.7\% video frame mAP with over 90 FPS on the UCF101-24. It also achieves 18.4 \% frame mAP with about 90 FPS on the AVA. As far as we know, YOWO-Nano is the fastest state-of-the-art action detector. Our code is available on https://github.com/yjh0410/PyTorch_YOWO.
