UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning

TL;DR

This paper introduces UCOD-DPL, an unsupervised camouflaged object detection method that uses a dynamic pseudo-label learning framework with a teacher-student setup, improving detection accuracy especially for small objects.

Contribution

The paper proposes a novel UCOD approach with adaptive pseudo-labels, adversarial decoding, and a double-refinement mechanism, addressing noise and semantic learning issues in unsupervised detection.

Findings

Outperforms existing unsupervised methods in camouflaged object detection.

Surpasses some fully-supervised methods in accuracy.

Effective in detecting small camouflaged objects.

Abstract

Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional layers as a simple decoder, leading to low performance compared to fully-supervised methods. We emphasize two drawbacks in these approaches: 1). The model is prone to fitting incorrect knowledge due to the pseudo-label containing substantial noise. 2). The simple decoder fails to capture and learn the semantic features of camouflaged objects, especially for small-sized objects, due to the low-resolution pseudo-labels and severe confusion between foreground and background pixels. To this end, we propose a UCOD method with a teacher-student framework via Dynamic Pseudo-label Learning called UCOD-DPL, which contains an Adaptive Pseudo-label Module (APM), a Dual-Branch Adversarial (DBA) decoder, and a Look-Twice mechanism. The APM module adaptively combines pseudo-labels generated by fixed strategies and the teacher model to prevent the model from overfitting incorrect knowledge while preserving the ability for self-correction; the DBA decoder takes adversarial learning of different segmentation objectives, guides the model to overcome the foreground-background confusion of camouflaged objects, and the Look-Twice mechanism mimics the human tendency to zoom in on camouflaged objects and performs secondary refinement on small-sized objects. Extensive experiments show that our method demonstrates outstanding performance, even surpassing some existing fully supervised methods. The code is available now.