Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection

TL;DR

This paper introduces HGINet, a hierarchical graph interaction network with dynamic token clustering, designed to improve camouflaged object detection by effectively distinguishing objects from backgrounds through hierarchical feature interaction.

Contribution

The paper proposes a novel hierarchical graph interaction transformer with dynamic token clustering for enhanced camouflaged object detection, addressing limitations of existing methods.

Findings

HGINet outperforms state-of-the-art methods on multiple datasets.

The dynamic token clustering improves local region distinguishability.

Hierarchical feature interaction enhances semantic understanding.

Abstract

Camouflaged object detection (COD) aims to identify the objects that seamlessly blend into the surrounding backgrounds. Due to the intrinsic similarity between the camouflaged objects and the background region, it is extremely challenging to precisely distinguish the camouflaged objects by existing approaches. In this paper, we propose a hierarchical graph interaction network termed HGINet for camouflaged object detection, which is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Specifically, we first design a region-aware token focusing attention (RTFA) with dynamic token clustering to excavate the potentially distinguishable tokens in the local region. Afterwards, a hierarchical graph interaction transformer (HGIT) is proposed to construct bi-directional aligned communication between hierarchical features in the latent interaction space for visual semantics enhancement. Furthermore, we propose a decoder network with confidence aggregated feature fusion (CAFF) modules, which progressively fuses the hierarchical interacted features to refine the local detail in ambiguous regions. Extensive experiments conducted on the prevalent datasets, i.e. COD10K, CAMO, NC4K and CHAMELEON demonstrate the superior performance of HGINet compared to existing state-of-the-art methods. Our code is available at https://github.com/Garyson1204/HGINet.