SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining
This work addresses the challenge of object detection with limited labeled data for computer vision researchers, offering incremental improvements in robustness to sparsity.
The paper tackles the problem of training object detectors with sparse annotations, which reduces performance, by proposing SparseDet, an end-to-end system that uses pseudo-positive mining to separate labeled and unlabeled regions, achieving state-of-the-art results with average improvements of 2.6, 3.9, and 9.6 mAP over previous methods on COCO splits.
Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that existing methods suffer at higher levels of sparsity in the data due to noisy pseudo-labels. To prevent this, we propose an end-to-end system that learns to separate the proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions thereby preventing the negative effects of noisy pseudo-labels. This novel approach has multiple advantages such as improved robustness to higher sparsity when compared to existing methods. We conduct exhaustive experiments on five splits on the PASCAL-VOC and COCO datasets achieving state-of-the-art performance. We also unify various splits used across literature for this task and present a standardized benchmark. On average, we improve by $2.6$, $3.9$ and $9.6$ mAP over previous state-of-the-art methods on three splits of increasing sparsity on COCO. Our project is publicly available at https://www.cs.umd.edu/~sakshams/SparseDet.