Soft Sampling for Robust Object Detection
arXiv: Computer Vision and Pattern Recognition, Volume abs/1806.06986, 2018.
We study the robustness of object detection under the presence of missing annotations. In this setting, the unlabeled object instances will be treated as background, which will generate an incorrect training signal for the detector. Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the...More
PPT (Upload PPT)