Out-of-Distribution Detection for Adaptive Computer Vision
| Autor: | Lind, Simon Kristoffersson, Triebel, Rudolph, Nardi, Luigi, Krueger, Volker |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| Zdroj: | In: Gade, R., Felsberg, M., K\"am\"ar\"ainen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13886. Springer, Cham |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1007/978-3-031-31438-4_21 |
| Popis: | It is well known that computer vision can be unreliable when faced with previously unseen imaging conditions. This paper proposes a method to adapt camera parameters according to a normalizing flow-based out-of-distibution detector. A small-scale study is conducted which shows that adapting camera parameters according to this out-of-distibution detector leads to an average increase of 3 to 4 percentage points in mAP, mAR and F1 performance metrics of a YOLOv4 object detector. As a secondary result, this paper also shows that it is possible to train a normalizing flow model for out-of-distribution detection on the COCO dataset, which is larger and more diverse than most benchmarks for out-of-distibution detectors. Comment: Published in Springer Lecture Notes for Computer Science Vol. 13886 as part of the conference proceedings for Scandinavian Conference on Image Analysis 2023 |
| Databáze: | arXiv |
| Externí odkaz: |
|