arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12176cs.CV
收藏

密集目标检测中的错位问题再思考

Rethinking the Misalignment Problem in Dense Object Detection

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Beijing Institute of Technology(北京理工大学)

Yang Yang, Min Li, Bo Meng, Junxing Ren, Degang Sun, Zihao Huang

摘要:

目标检测的目的是对给定图像中的目标进行定位和分类,这两项任务对不同的目标区域敏感。因此,有些位置预测高质量的边界框,但分类得分较低,而有些位置则恰恰相反。两个任务之间存在不对准,并且它们的特征在空间上纠缠。为了解决错位问题,我们提出了一个插件空间解纠缠和任务对齐操作(SALT)。通过预测位于每个任务敏感区域中的两个任务感知点集,SALT可以重新分配这些区域的特征,并将它们与相应的锚点对齐。因此,这两个任务的功能在空间上对齐和分离。为了最小化两个回归阶段之间的差异,我们提出了一种自蒸馏回归(SDR)损失,可以将知识从精细回归结果转移到粗略回归结果。在SALT和SDR丢失的基础上,我们提出了SALT-Net,它显式地利用任务对齐的点集特征来获得准确的检测结果。在MS-COCO数据集上的大量实验表明,我们提出的方法可以通过$\sim$ 2 AP一致地提高不同的最先进的密集检测器。值得注意的是,具有Res 2Net-101-DCN主干的SALT-Net在MS-COCO测试开发中实现了53.8 AP。

英文摘要:

Object detection aims to localize and classify the objects in a given image, and these two tasks are sensitive to different object regions. Therefore, some locations predict high-quality bounding boxes but low classification scores, and some locations are quite the opposite. A misalignment exists between the two tasks, and their features are spatially entangled. In order to solve the misalignment problem, we propose a plug-in Spatial-disentangled and Task-aligned operator (SALT). By predicting two task-aware point sets that are located in each task's sensitive regions, SALT can reassign features from those regions and align them to the corresponding anchor point. Therefore, features for the two tasks are spatially aligned and disentangled. To minimize the difference between the two regression stages, we propose a Self-distillation regression (SDR) loss that can transfer knowledge from the refined regression results to the coarse regression results. On the basis of SALT and SDR loss, we propose SALT-Net, which explicitly exploits task-aligned point-set features for accurate detection results. Extensive experiments on the MS-COCO dataset show that our proposed methods can consistently boost different state-of-the-art dense detectors by $\sim$2 AP. Notably, SALT-Net with Res2Net-101-DCN backbone achieves 53.8 AP on the MS-COCO test-dev.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑