Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection
Authors:
Preprint
Abstract
Camouflaged object detection (COD) presents a persistent challenge in accurately identifying objects that seamlessly blend into their surroundings. However, most existing COD models overlook the fact that visual systems operate within a genuine 3D environment. The scene depth inherent in a single 2D image provides rich spatial clues that can assist in the detection of camouflaged objects. Therefore, we propose a novel depth-perception attention fusion network that leverages the depth map as an auxiliary input to enhance the network's ability to perceive 3D information, which is typically challenging for the human eye to discern from 2D images. The network uses a trident-branch encoder to extract chromatic and depth information and their communications. Recognizing that certain regions of a depth map may not effectively highlight the camouflaged object, we introduce a depth-weighted cross-attention fusion module to dynamically adjust the fusion weights on depth and RGB feature maps. To keep the model simple without compromising effectiveness, we design a straightforward feature aggregation decoder that adaptively fuses the enhanced aggregated features. Experiments demonstrate the significant superiority of our proposed method over other states of the arts, which further validates the contribution of depth information in camouflaged object detection. The code will be available at https://github.com/xinran-liu00/DAF-Net.Keywords
All Related Versions
- Version 1, 2024-05-09, ArXiv
- Published version: Image and Vision Computing, 143.
This publication has 26 references indexed in Scilit:
- Deep Gradient Learning for Efficient Camouflaged Object DetectionMachine Intelligence Research, 2023
- Cross-modal hierarchical interaction network for RGB-D salient object detectionPattern Recognition, 2022
- Single image depth estimation: An overviewDigital Signal Processing, 2022
- Double cross-modality progressively guided network for RGB-D salient object detectionImage and Vision Computing, 2022
- RGB-D salient object detection: A surveyComputational Visual Media, 2021
- Attention-guided RGBD saliency detection using appearance informationImage and Vision Computing, 2020
- Salient object detection for RGB-D image by single stream recurrent convolution neural networkNeurocomputing, 2019
- Anabranch network for camouflaged object segmentationComputer Vision and Image Understanding, 2019
- Depth-aware saliency detection using convolutional neural networksJournal of Visual Communication and Image Representation, 2019
- Pest identification via deep residual learning in complex backgroundComputers and Electronics in Agriculture, 2017