论文标题
现代对象探测器的经验上限，错误诊断和不变性分析
Empirical Upper Bound, Error Diagnosis and Invariance Analysis of Modern Object Detectors
论文作者
论文摘要
对象检测仍然是计算机视觉中最臭名昭著的开放问题之一。尽管近年来准确性取得了长足的进步，但现代对象探测器已经开始饱和流行的基准测试，这提出了我们可以使用深度学习工具和技巧可以达到多远的问题。在这里，通过使用2个最先进的对象检测基准，并在4个大型数据集上分析15个以上的模型，我们i）仔细确定AP中的上限，即VOC的上限为91.6％（Test2007），可可（Val2017）为78.2％，在OpenImimages v4（v4（v4）（验证）上为58.9％（效果）。这些数字比最佳模型的地图要好得多（VOC的47.9％，可可的可可; ious = .5：.05：.95），ii），ii）以新颖和直觉的方式表征对象探测器中错误的来源，并发现与其他类别的分类错误（混淆和误解）相比，差异和权衡了误差的差异，并且犯了差异，并且犯了错误的差异，并且二重要的差异是错误的。当删除对象上下文，将对象放置在不一致的背景中以及图像被垂直模糊或翻转时，模型的不变性属性。我们发现，模型在空区域上产生了很多框，而对于检测小物体而言，上下文比大型对象更为重要。我们的工作利用了对象检测与对象识别之间的紧密关系，并为建立更好的模型提供了见解。我们的代码可在https://github.com/aliborji/deetctuctionupper bound.git上公开获取。
Object detection remains as one of the most notorious open problems in computer vision. Despite large strides in accuracy in recent years, modern object detectors have started to saturate on popular benchmarks raising the question of how far we can reach with deep learning tools and tricks. Here, by employing 2 state-of-the-art object detection benchmarks, and analyzing more than 15 models over 4 large scale datasets, we I) carefully determine the upper bound in AP, which is 91.6% on VOC (test2007), 78.2% on COCO (val2017), and 58.9% on OpenImages V4 (validation), regardless of the IOU threshold. These numbers are much better than the mAP of the best model (47.9% on VOC, and 46.9% on COCO; IOUs=.5:.05:.95), II) characterize the sources of errors in object detectors, in a novel and intuitive way, and find that classification error (confusion with other classes and misses) explains the largest fraction of errors and weighs more than localization and duplicate errors, and III) analyze the invariance properties of models when surrounding context of an object is removed, when an object is placed in an incongruent background, and when images are blurred or flipped vertically. We find that models generate a lot of boxes on empty regions and that context is more important for detecting small objects than larger ones. Our work taps into the tight relationship between object detection and object recognition and offers insights for building better models. Our code is publicly available at https://github.com/aliborji/Deetctionupper bound.git.
