Reference Prompted Model Adaptation for Referring Camouflaged Object Detection

The goal of referring camouflaged object detection is to identify and segment the specified object hidden in the surroundings given text or images as references. The previous method still faces limitations in learning discriminative object features and comprehensively exploiting reference information due to coarse reference-image fusion upon disunified network components. In this paper, we propose a novel Reference Prompted Model Adaptation (RPMA) pipeline that employs rich and fine-grained semantic knowledge in a generic segmentation network to enhance the Ref-COD model’s capability. Within RPMA, we design a Cross Reference Adapter (CRA) to integrate reference information into the generic segmentation network to prompt reference-relevant camouflaged image features, and also devise a Reference-guided Dynamic Convolution (RDC) for foreground-background segmentation via reference-generated kernels. Extensive experiments on the Ref-COD benchmark show that our method achieves new state-of-the-art performance.

I. Introduction

Camouflaged Object Detection [1] (COD) aims to identify and segment objects that are naturally hidden in their surrounding environment, which is difficult even for humans to distinguish the camouflaged objects without explicit targets. Therefore, the task of Ref-COD [2] is recently proposed to guide the detection process with additional text or images as references (e.g., class name or salient images belonging to the target class of camouflaged object), accomplishing more specified and applicable COD.