Just a Hint: Point-Supervised Camouflaged Object Detection

TL;DR

This paper introduces a point-supervised method for camouflaged object detection that reduces annotation effort by expanding point annotations and using attention regulation and contrastive learning, achieving superior results.

Contribution

It presents a novel point-supervised approach with attention regulation and contrastive learning for camouflaged object detection, reducing annotation effort and improving accuracy.

Findings

Outperforms several weakly-supervised methods on three COD benchmarks.

Effectively expands point annotations to hint areas for better localization.

Utilizes unsupervised contrastive learning to stabilize feature representations.

Abstract

Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a remarkably challenging task for models but also for human annotators, requiring huge efforts to provide pixel-wise annotations. To alleviate the heavy annotation burden, we propose to fulfill this task with the help of only one point supervision. Specifically, by swiftly clicking on each object, we first adaptively expand the original point-based annotation to a reasonable hint area. Then, to avoid partial localization around discriminative parts, we propose an attention regulator to scatter model attention to the whole object through partially masking labeled regions. Moreover, to solve the unstable feature representation of camouflaged objects under only point-based annotation, we perform unsupervised contrastive learning based on differently augmented image pairs (e.g. changing color or doing translation). On three mainstream COD benchmarks, experimental results show that our model outperforms several weakly-supervised methods by a large margin across various metrics.