Generalized Open-World Semi-Supervised Object Detection

TL;DR

This paper introduces a novel open-world semi-supervised object detection framework that detects and learns from both in-distribution and out-of-distribution classes, improving detection accuracy in real-world scenarios.

Contribution

It proposes an ensemble-based OOD detection method and an adaptable semi-supervised learning framework that incorporates OOD data into training, advancing open-world object detection.

Findings

Competitive OOD detection performance against state-of-the-art algorithms.

Significant improvement in semi-supervised learning for both ID and OOD classes.

Effective integration of OOD data enhances overall detection accuracy.

Abstract

Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance in real-world scenarios where unseen classes (out-of-distribution or OOD classes) may appear. In such cases, OOD data is often misclassified as ID, thus harming the ID classes accuracy. Open-set methods address this limitation by filtering OOD data to improve ID performance, thereby limiting the learning process to ID classes. We extend this to a more natural open-world setting, where the OOD classes are not only detected but also incorporated into the learning process. Specifically, we explore two key questions: 1) how to accurately detect OOD samples, and, most importantly, 2) how to effectively learn from the OOD samples in a semi-supervised object detection pipeline without compromising ID accuracy. To address this, we introduce an ensemble-based OOD Explorer for detection and classification, and an adaptable semi-supervised object detection framework that integrates both ID and OOD data. Through extensive evaluation on different open-world scenarios, we demonstrate that our method performs competitively against state-of-the-art OOD detection algorithms and also significantly boosts the semi-supervised learning performance for both ID and OOD classes.