The Middle Child Problem: Revisiting Parametric Min-cut and Seeds for Object Proposals

Object proposals have recently fueled the progress in detection performance. These proposals aim to provide category-agnostic localizations for all objects in an image. One way to generate proposals is to perform parametric min-cuts over seed locations. This paper demonstrates that standard parametric-cut models are ineffective in obtaining medium-sized objects, which we refer to as the middle child problem. We propose a new energy minimization framework incorporating geodesic distances between segments which solves this problem. In addition, we introduce a new superpixel merging algorithm which can generate a small set of seeds that reliably cover a large number of objects of all sizes. We call our method POISE- "Proposals for Objects from Improved Seeds and Energies." POISE enables parametric min-cuts to reach their full potential. On PASCAL VOC it generates similar to 2,640 segments with an average overlap of 0.81, whereas the closest competing methods require more than 4,200 proposals to reach the same accuracy [24, 30]. We show detailed quantitative comparisons against 5 state-of-the-art methods on PASCAL VOC and Microsoft COCO segmentation challenges.