A Mask-RCNN Baseline for Probabilistic Object Detection

The Probabilistic Object Detection Challenge evaluates object detection methods using a new evaluation measure, Probability-based Detection Quality (PDQ), on a new synthetic image dataset. We present our submission to the challenge, a fine-tuned version of Mask-RCNN with some additional post-processing. Our method, submitted under username pammirato, is currently second on the leaderboard with a score of 21.432, while also achieving the highest spatial quality and average overall quality of detections. We hope this method can provide some insight into how detectors designed for mean average precision (mAP) evaluation behave under PDQ, as well as a strong baseline for future work.

[1]  Yuandong Tian,et al.  Building Generalizable Agents with a Realistic and Rich 3D Environment , 2018, ICLR.

[2]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[3]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[4]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Thomas A. Funkhouser,et al.  Semantic Scene Completion from a Single Depth Image , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Peter I. Corke,et al.  Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation , 2018, ArXiv.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Ali Farhadi,et al.  AI2-THOR: An Interactive 3D Environment for Visual AI , 2017, ArXiv.

[9]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[10]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.