Feature Aggregation and Propagation Network for Camouflaged Object Detection

TL;DR

This paper introduces FAP-Net, a novel network for camouflaged object detection that uses boundary guidance, multi-scale feature aggregation, and cross-level fusion to improve segmentation accuracy, outperforming existing models on benchmark datasets.

Contribution

The paper proposes a comprehensive end-to-end framework with novel modules for boundary modeling, multi-scale feature aggregation, and cross-level feature fusion, advancing camouflaged object detection techniques.

Findings

FAP-Net outperforms state-of-the-art COD models on benchmark datasets.

The Boundary Guidance Module enhances boundary feature representation.

The model can be extended successfully to polyp segmentation tasks.

Abstract

Camouflaged object detection (COD) aims to detect/segment camouflaged objects embedded in the environment, which has attracted increasing attention over the past decades. Although several COD methods have been developed, they still suffer from unsatisfactory performance due to the intrinsic similarities between the foreground objects and background surroundings. In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection. Specifically, we propose a Boundary Guidance Module (BGM) to explicitly model the boundary characteristic, which can provide boundary-enhanced features to boost the COD performance. To capture the scale variations of the camouflaged objects, we propose a Multi-scale Feature Aggregation Module (MFAM) to characterize the multi-scale information from each layer and obtain the aggregated feature representations. Furthermore, we propose a Cross-level Fusion and Propagation Module (CFPM). In the CFPM, the feature fusion part can effectively integrate the features from adjacent layers to exploit the cross-level correlations, and the feature propagation part can transmit valuable context information from the encoder to the decoder network via a gate unit. Finally, we formulate a unified and end-to-end trainable framework where cross-level features can be effectively fused and propagated for capturing rich context information. Extensive experiments on three benchmark camouflaged datasets demonstrate that our FAP-Net outperforms other state-of-the-art COD models. Moreover, our model can be extended to the polyp segmentation task, and the comparison results further validate the effectiveness of the proposed model in segmenting polyps. The source code and results will be released at https://github.com/taozh2017/FAPNet.