Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by cropping the input (RCNN), partial context by cropping the featuremap (two-stage methods) and full context without any cropping (single-stage methods). We systematically evaluate the effect of context for each deep detector category. We create a fully controlled dataset for varying context and investigate the context for deep detectors. We also evaluate gradually removing the background context and the foreground object on MS COCO. We demonstrate that single-stage and two-stage object detectors can and will use the context by virtue of their large receptive field. Thus, choosing the best object detector may depend on the application context.

翻译：深物体探测器对场景环境进行不同的识别。在本文件中,我们将物体探测器按上下文使用分为三类:输入(RCNNN)不切实际,特性图(两阶段方法)不切实际(两阶段方法)不切实际,整个环境不切实际(单阶段方法)不切实际。我们系统地评估每个深探测器类别的上下文效果。我们为不同背景创建一个完全控制的数据集,并调查深探测器的上下文。我们还评估了MS COCO的背景背景和地表物体的逐步去除情况。我们证明单级和两阶段物体探测器能够并且将使用上下文,因为其大面积的可接收场。因此,选择最佳物体探测器可能取决于应用环境。