Determinantal Point Process as an alternative to NMS
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2020
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914840321196032 |
|---|---|
| author | Some, Samik Gupta, Mithun Das Namboodiri, Vinay P. |
| author_facet | Some, Samik Gupta, Mithun Das Namboodiri, Vinay P. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2008_11451 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Determinantal Point Process as an alternative to NMS Some, Samik Gupta, Mithun Das Namboodiri, Vinay P. Computer Vision and Pattern Recognition 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. |
| title | Determinantal Point Process as an alternative to NMS |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2008.11451 |