Semi-supervised Camouflaged Object Detection from Noisy Data

Yuanbin Fu, Jie Ying, Houlei Lv, Xiaojie Guo

Abstract: Most of previous camouflaged object detection methods heavily lean upon large-scale manually-labeled training samples, which are notoriously difficult to obtain. Even worse, the reliability of labels is compromised by the inherent challenges in accurately annotating concealed targets that exhibit high similarities with their surroundings. To overcome these shortcomings, this paper develops the first semi-supervised camouflaged object detection framework, which requires merely a small amount of samples even having noisy/incorrect annotations. Specifically, on the one hand, we introduce an innovative pixel-level loss re-weighting technique to reduce possible negative impacts from imperfect labels, through a window-based voting strategy. On the other hand, we take advantages of ensemble learning to explore robust features against noises/outliers, thereby generating relatively reliable pseudo labels for unlabelled images. Extensive experimental results on four benchmark datasets have been conducted.

Primary Subject Area: [Content] Media Interpretation

Secondary Subject Area: [Content] Media Interpretation

Relevance To Conference: This work is the first attempt to learn a semi-supervised camouflaged object detection model, which is beneficial for the relief of heavy annotation burden. To tackle the noisy annotations exist in the labelled set, the techniques of loss re-weighting and model ensemble are used to explore robust information. Extensive experimental results demonstrate that our method is able to achieve competitive performance compared to fully-supervised models.

Submission Number: 1365