Soft Sampling for Robust Object Detection
This addresses robustness issues in object detection for real-world datasets with incomplete annotations, offering an incremental improvement.
The paper tackles the problem of object detection robustness when annotations are missing, showing that dropping 30% of annotations causes only a 5% performance drop in Faster-RCNN on PASCAL VOC, and proposes Soft Sampling to re-weight gradients, improving performance by over 3% on OpenImagesV3.
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 performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset. We provide a detailed explanation for this result. To further bridge the performance gap, we propose a simple yet effective solution, called Soft Sampling. Soft Sampling re-weights the gradients of RoIs as a function of overlap with positive instances. This ensures that the uncertain background regions are given a smaller weight compared to the hardnegatives. Extensive experiments on curated PASCAL VOC datasets demonstrate the effectiveness of the proposed Soft Sampling method at different annotation drop rates. Finally, we show that on OpenImagesV3, which is a real-world dataset with missing annotations, Soft Sampling outperforms standard detection baselines by over 3%.