Determinantal Point Process as an alternative to NMS
arXiv:2008.11451
Abstract
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.
Published in BMVC 2020
References in corpus (6)
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Learning Determinantal Point Processes
- Do Less, Get More: Streaming Submodular Maximization with Subsampling
- Learning non-maximum suppression
- Rates of estimation for determinantal point processes
- Learning Detection with Diverse Proposals