SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining

TL;DR

SparseDet introduces a novel end-to-end approach using pseudo-positive mining to improve object detection performance under sparse annotations, effectively handling noisy pseudo-labels and achieving state-of-the-art results.

Contribution

The paper proposes a new method that separates labeled and unlabeled proposals with self-supervised learning, enhancing robustness to high sparsity in object detection.

Findings

Achieves state-of-the-art performance on PASCAL-VOC and COCO datasets.

Improves mAP by 2.6, 3.9, and 9.6 over previous methods on different sparsity splits.

Provides a standardized benchmark for sparse annotation scenarios.

Abstract

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.