论文标题
增强模型学习中的几何因素和对象检测和实例分段的推断
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
论文作者
论文摘要
基于深度学习的对象检测和实例细分已经取得了前所未有的进步。在本文中，我们提出了完整的IOU（CIOU）损失和集群NMS，以增强边界盒回归和非最大抑制（NMS）的几何因素，从而在没有推理效率的情况下，导致平均精度（AP）和平均召回率（AR）的显着增长。特别是，我们考虑了三个几何因素，即重叠面积，归一化的中心点距离和纵横比，这对于测量对象检测和实例分割中的边界框回归至关重要。然后将三个几何因素纳入CIOU损失，以更好地区分困难回归案例。与广泛采用的$ \ ell_n $ norm损失和基于IOU的损失相比，使用CIOU损失对深层模型的训练会导致AP和AR的改进。此外，我们提出了群集NMS，其中推理过程中的NMS是通过隐式聚类的检测到的框来完成的，通常需要更少的迭代。群集NMS由于其纯粹的GPU实施而非常有效，并且可以合并几何因素以改善AP和AR。在实验中，CIOU丢失和群集NM已应用于最新的实例分割（例如Yolact和BlendMask-RT），以及对象检测（例如Yolo V3，SSD，SSD和更快的R-CNN）模型。以MS Coco为例，我们的方法以+1.7 AP和+6.2 AR $ _ {100} $的对象检测而获得性能的增长，+0.9 AP和+3.5 AR $ _ {100} $用于段段，一个NVIDIA GTX 1080TX 1080TITI的27.1 fps。所有源代码和训练有素的模型均可在https://github.com/zzh-tju/ciou上获得
Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, i.e., overlap area, normalized central point distance and aspect ratio, which are crucial for measuring bounding box regression in object detection and instance segmentation. The three geometric factors are then incorporated into CIoU loss for better distinguishing difficult regression cases. The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted $\ell_n$-norm loss and IoU-based loss. Furthermore, we propose Cluster-NMS, where NMS during inference is done by implicitly clustering detected boxes and usually requires less iterations. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR. In the experiments, CIoU loss and Cluster-NMS have been applied to state-of-the-art instance segmentation (e.g., YOLACT and BlendMask-RT), and object detection (e.g., YOLO v3, SSD and Faster R-CNN) models. Taking YOLACT on MS COCO as an example, our method achieves performance gains as +1.7 AP and +6.2 AR$_{100}$ for object detection, and +0.9 AP and +3.5 AR$_{100}$ for instance segmentation, with 27.1 FPS on one NVIDIA GTX 1080Ti GPU. All the source code and trained models are available at https://github.com/Zzh-tju/CIoU
