The role of context for object detection and semantic segmentation in the wild

In this paper, we are interested in further analyzing the effect of context in detection and segmentation approaches. Towards this goal, we label every pixel of the training and validation sets of the PASCAL VOC 2010 main challenge with a semantic class (examples are shown in Figure 1). We selected PASCAL as our testbed as it has served as the benchmark for detection and segmentation in the commu-nity for years (over 600 citations and tens of teams com-peting in the challenges each year). Our analysis shows that our new dataset is much more challenging than existing ones (e.g., Barcelona [6], SUN [7], SIFT flow [5]), as it has higher class entropy, less pixels are labeled as “stuff ” and instead belong to a wide variety of object categories beyond the 20 PASCAL object classes. We analyze the ability of state-of-the-art methods [6, 1