Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection
By Dimity Miller, Feras Dayoub, Michael Milford, Niko Sünderhauf. 2018
119 citations recorded by the source corpus.
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples, this is not the case for object detection, where detection sample bounding boxes must be accurately associated and merged. A weak merging strategy can significantly degrade the performance of the detector and yield an unreliable uncertainty measure. This paper provides the first in-depth investigation of the effect of different association and merging strategies. We compare different combinations of three spatial and two semantic affinity measures with four clustering methods for MC Dropout with a Single Shot Multi-Box Detector. Our results show that the correct choice of affinity-clustering combination can greatly improve the effectiveness of the classification and spatial uncertainty estimation and the resulting object detection performance. We base our evaluation on a new mix of datasets that emulate near open-set conditions (semantically similar unknown classes), distant open-set conditions (semantically dissimilar unknown classes) and the common closed-set conditions (only known classes).
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Klaus C. J. Dietmayer
- Di Feng
- Xuefeng Du
- Mu Cai
- Zhaoning Wang
- Yixuan Li
- Niko Sünderhauf
- Lars Rosenbaum
Citations in the corpus
- VOS: Learning What You Don't Know by Virtual Outlier Synthesis (2022, methodology): “Several works (Dhamija et al., 2020; Miller et al., 2019; 2018; Hall et al., 2020; Deepshikha et al., 2021) used approximate Bayesian methods, such as MC-Dropout (Gal & Ghahramani, 2016) for OOD detection.”
- Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges (2019, methodology): “It has been applied to semantic segmentation [174] and open-world object detection problems [175], [176].”
- A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving (2020, methodology): “[7] to evaluate probabilistic object detectors.”
- Probabilistic Object Detection: Definition and Evaluation (2018, methodology): “Most of the proposed methods, except [29, 42], deal with pixel-wise classification.”