B2Net: Camouflaged Object Detection via Boundary Aware and Boundary Fusion

TL;DR

B2Net is a boundary-aware network for camouflaged object detection that enhances boundary accuracy through multi-stage boundary modules, feature enhancement, and cross-scale fusion, outperforming existing methods.

Contribution

The paper introduces B2Net, a novel boundary-aware architecture with modules for boundary refinement and multi-scale fusion, improving camouflaged object detection accuracy.

Findings

Outperforms 15 state-of-the-art methods on benchmark datasets.

Effective boundary refinement improves detection accuracy.

Boundary modules enhance feature discriminability.

Abstract

Camouflaged object detection (COD) aims to identify objects in images that are well hidden in the environment due to their high similarity to the background in terms of texture and color. However, existing most boundary-guided camouflage object detection algorithms tend to generate object boundaries early in the network, and inaccurate edge priors often introduce noises in object detection. Address on this issue, we propose a novel network named B2Net aiming to enhance the accuracy of obtained boundaries by reusing boundary-aware modules at different stages of the network. Specifically, we present a Residual Feature Enhanced Module (RFEM) with the goal of integrating more discriminative feature representations to enhance detection accuracy and reliability. After that, the Boundary Aware Module (BAM) is introduced to explore edge cues twice by integrating spatial information from low-level features and semantic information from high-level features. Finally, we design the Cross-scale Boundary Fusion Module(CBFM) that integrate information across different scales in a top-down manner, merging boundary features with object features to obtain a comprehensive feature representation incorporating boundary information. Extensive experimental results on three challenging benchmark datasets demonstrate that our proposed method B2Net outperforms 15 state-of-art methods under widely used evaluation metrics. Code will be made publicly available.