Penalizing Proposals using Classifiers for Semi-Supervised Object Detection

TL;DR

This paper introduces a modified loss function for semi-supervised object detection that incorporates a confidence metric for machine-generated labels, significantly improving detection accuracy with limited labeled data.

Contribution

The authors propose a novel loss function that integrates annotation confidence, enhancing semi-supervised object detection performance over existing methods.

Findings

Achieved a 4% mAP improvement with 25% labeled data.

Achieved a 10% mAP improvement with 50% labeled data.

Validated effectiveness across various test sets.

Abstract

Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a small amount of gold-standard labels and a large unlabelled dataset used to generate silver-standard labels. But training on the silver standard labels does not produce good results, because they are machine-generated annotations. In this work, we design a modified loss function to train on large silver standard annotated sets generated by a weak annotator. We include a confidence metric associated with the annotation as an additional term in the loss function, signifying the quality of the annotation. We test the effectiveness of our approach on various test sets and use numerous variations to compare the results with some of the current approaches to object detection. In comparison with the baseline where no confidence metric is used, we achieved a 4% gain in mAP with 25% labeled data and 10% gain in mAP with 50% labeled data by using the proposed confidence metric.