Determinantal Point Process as an alternative to NMS
This addresses a bottleneck in object detection for computer vision applications, but appears incremental as it modifies an existing step.
The paper tackled the problem of non-maximum suppression (NMS) in object detection by proposing a determinantal point process (DPP) alternative, resulting in consistent improvements to state-of-the-art pipelines.
We present a determinantal point process (DPP) inspired alternative to non-maximum suppression (NMS) which has become an integral step in all state-of-the-art object detection frameworks. DPPs have been shown to encourage diversity in subset selection problems. We pose NMS as a subset selection problem and posit that directly incorporating DPP like framework can improve the overall performance of the object detection system. We propose an optimization problem which takes the same inputs as NMS, but introduces a novel sub-modularity based diverse subset selection functional. Our results strongly indicate that the modifications proposed in this paper can provide consistent improvements to state-of-the-art object detection pipelines.