B2Net: Camouflaged Object Detection via Boundary Aware and Boundary Fusion
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Camouflaged object detection via cross-level refinement and interaction networkImage and Vision Computing, 2024
- Local to global purification strategy to realize collaborative camouflaged object detectionComputer Vision and Image Understanding, 2024
- PVT v2: Improved baselines with pyramid vision transformerComputational Visual Media, 2022
- Deep Texton-Coherence Network for Camouflaged Object DetectionIEEE Transactions on Multimedia, 2022
- Boundary-Guided Camouflaged Object Detection2022
- Context-aware Cross-level Fusion Network for Camouflaged Object Detection2021
- Animal camouflage: current issues and new perspectivesPhilosophical Transactions of the Royal Society B: Biological Sciences, 2008