Out-of-Distribution Detection for Adaptive Computer Vision
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 16 May 2023.
Builds on
13 of 20 references.
References · 13
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2016Density estimation using Real NVPcited by 2,029
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
- 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
- 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
- 2020Safe Robot Navigation via Multi-Modal Anomaly Detectioncited by 33
- 2018Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertaintycited by 14
1 more
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.