IdeNet: Making Neural Network Identify Camouflaged Objects Like Creatures
- 30 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 4824-4839
Abstract
Camouflaged objects often blend in with their surroundings, making the perception of a camouflaged object a more complex procedure. However, most neural-network-based methods that simulate the visual information processing pathway of creatures only roughly define the general process, which deficiently reproduces the process of identifying camouflaged objects. How to make modeled neural networks perceive camouflaged objects as effectively as creatures is a significant topic that deserves further consideration. After meticulous analysis of biological visual information processing, we propose an end-to-end prudent and comprehensive neural network, termed IdeNet, to model the critical information processing. Specifically, IdeNet divides the entire perception process into five stages: information collection, information augmentation, information filtering, information localization, and information correction and object identification. In addition, we design tailored visual information processing mechanisms for each stage, including the information augmentation module (IAM), the information filtering module (IFM), the information localization module (ILM), and the information correction module (ICM), to model the critical visual information processing and establish the inextricable association of biological behavior and visual information processing. The extensive experiments show that IdeNet outperforms state-of-the-art methods in all benchmarks, demonstrating the effectiveness of the five-stage partitioning of visual information processing pathway and the tailored visual information processing mechanisms for camouflaged object detection. Our code is publicly available at: https://github.com/whyandbecause/IdeNet.Keywords
Funding Information
- National Natural Science Foundation of China (62061146001, 62372102, 62232004, 61972083, 62202096, 62072103)
- Jiangsu Provincial Key Research and Development Program (BE2022680)
- China Computer Federation (CCF)-Huawei Populus Grove Fund, Fundamental Research Funds for the Central Universities (242024k30022)
- Jiangsu Provincial Key Laboratory of Network and Information Security (BM2003201)
- Collaborative Innovation Center of Novel Software Technology and Industrialization
This publication has 74 references indexed in Scilit:
- Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration NetworkPattern Recognition, 2022
- Synthetic data augmentation for surface defect detection and classification using deep learningJournal of Intelligent Manufacturing, 2020
- PraNet: Parallel Reverse Attention Network for Polyp Segmentation2020
- Kvasir-SEG: A Segmented Polyp Dataset2019
- Anabranch network for camouflaged object segmentationComputer Vision and Image Understanding, 2019
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physiciansComputerized Medical Imaging and Graphics, 2015
- Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancerInternational Journal of Computer Assisted Radiology and Surgery, 2013
- What, if anything, is the adaptive function of countershading?Animal Behaviour, 2004
- ‘What’ and ‘where’ in the human brainCurrent Opinion in Neurobiology, 1994