Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection

TL;DR

This paper introduces CFL-Detector, a novel approach for open-set semi-supervised object detection that uses contrastive feature clustering and logits-level uncertainty to better distinguish in-distribution and out-of-distribution classes, improving detection accuracy.

Contribution

The paper proposes a simple yet effective method combining feature-level contrastive clustering and logits-level uncertainty loss for open-set SSOD, addressing OOD class misclassification.

Findings

Achieves state-of-the-art performance on open-set SSOD benchmarks.

Effectively distinguishes in-distribution and out-of-distribution classes.

Improves detection accuracy in open-set scenarios.

Abstract

Current Semi-Supervised Object Detection (SSOD) methods enhance detector performance by leveraging large amounts of unlabeled data, assuming that both labeled and unlabeled data share the same label space. However, in open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. To alleviate this issue, we propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector). Specifically, we introduce a feature-level clustering method using contrastive loss to clarify vector boundaries in the feature space and highlight class differences. Additionally, by optimizing the logits-level uncertainty classification loss, the model enhances its ability to effectively distinguish between ID and OOD classes. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing methods.