Abstract
Camouflaged object detection (COD) is important as it has various potential applications. Unlike salient object detection (SOD), which tries to identify visually salient objects, COD tries to detect objects that are visually very similar to the surrounding background. We observe that recent COD methods try to fuse features from different levels using some context aggregation strategies originally developed for SOD. Such an approach, however, may not be appropriate for COD as these existing context aggregation strategies are good at detecting distinctive objects while weakening the features from less discriminative objects. To address this problem, we propose in this article to exploit frequency learning to suppress the confusing high-frequency texture information, to help separate camouflaged objects from their surrounding background, and a frequency-based method, called FBNet, for camouflaged object detection. Specifically, we design a frequency-aware context aggregation (FACA) module to suppress high-frequency information and aggregate multi-scale features from a frequency perspective, an adaptive frequency attention (AFA) module to enhance the features of the learned important frequency components, and a gradient-weighted loss function to guide the proposed method to pay more attention to contour details. Experimental results show that our model outperforms relevant state-of-the-art methods.
- [1] 2018. Animal Camouflage Analysis: Chameleon Database. Unpublished Manuscript 2, 6 (2018), 7.Google Scholar
- [2] . 2019. Hybrid task cascade for instance segmentation. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [3] . 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 4 (2017), 834–848.Google Scholar
- [4] . 2020. Global context-aware progressive aggregation network for salient object detection. In Proceedings of the AAAI.Google Scholar
Cross Ref
- [5] . 2020. Global context-aware progressive aggregation network for salient object detection. In Proceedings of the AAAI.Google Scholar
Cross Ref
- [6] . 2018. Context contrasted feature and gated multi-scale aggregation for scene segmentation. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [7] . 2019. Deep residual learning in the jpeg transform domain. In Proceedings of the ICCV. 3484–3493.Google Scholar
Cross Ref
- [8] . 2017. Structure-measure: A new way to evaluate foreground maps. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [9] . 2018. Enhanced-alignment measure for binary foreground map evaluation. In Proceedings of the IJCAI.Google Scholar
Cross Ref
- [10] . 2020. Camouflaged object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [11] . 2022. DMT: Dynamic mutual training for semi-supervised learning. Pattern Recognition (2022), 108777.
DOI: Google ScholarDigital Library
- [12] . 2018. Image editing by object-aware optimal boundary searching and mixed-domain composition. Computational Visual Media 4, 1 (2018), 71–82.Google Scholar
Cross Ref
- [13] . 2019. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In Proceedings of the ICLR. Retrieved from https://openreview.net/forum?id=Bygh9j09KX.Google Scholar
- [14] . 2022. Learning semantic associations for mirror detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [15] . 2017. Mask r-cnn. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [16] . 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the ICCV. 1026–1034.Google Scholar
Digital Library
- [17] . 2016. Deep residual learning for image recognition. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [18] . 2018. Squeeze-and-excitation networks. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [19] . 2019. Mask scoring r-cnn. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [20] . 2019. Anabranch network for camouflaged object segmentation. CVIU 184 (2019), 45–56.Google Scholar
Digital Library
- [21] . 2021. Uncertainty-aware joint salient object and camouflaged object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [22] . 2014. Single image layer separation using relative smoothness. In Proceedings of the CVPR.Google Scholar
Digital Library
- [23] . 2021. Rich context aggregation with reflection prior for glass surface detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [24] . 2020. Progressive mirror detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [25] . 2017. Feature pyramid networks for object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [26] . 2019. A simple pooling-based design for real-time salient object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [27] . 2018. Picanet: Learning pixel-wise contextual attention for saliency detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [28] . 2018. Receptive field block net for accurate and fast object detection. In Proceedings of the ECCV. 385–400.Google Scholar
Digital Library
- [29] . 2015. Parsenet: Looking wider to see better. arXiv:1506.04579. Retrieved from https://arxiv.org/abs/1506.04579.Google Scholar
- [30] . 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the ICCV (2021).Google Scholar
- [31] . 2016. Understanding the effective receptive field in deep convolutional neural networks. In Proceedings of the NeurIPS.Google Scholar
- [32] . 2021. Simultaneously localize, segment and rank the camouflaged objects. In Proceedings of the CVPR.Google Scholar
- [33] . 2014. How to evaluate foreground maps? In Proceedings of the CVPR.Google Scholar
Digital Library
- [34] . 2021. Camouflaged object segmentation with distraction mining. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [35] . 2020. Don’t hit me! glass detection in real-world scenes. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [36] . 2011. Study on the camouflaged target detection method based on 3D convexity. Modern Applied Science 5, 4 (2011), 152.Google Scholar
Cross Ref
- [37] . 2020. Multi-scale interactive network for salient object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [38] . 2019. BASNet: Boundary-aware salient object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [39] . 2020. FcaNet: Frequency channel attention networks. arXiv:2012.11879. Retrieved from https://arxiv.org/abs/2012.11879.Google Scholar
- [40] . 2019. Selectivity or invariance: Boundary-aware salient object detection. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [41] . 2022. Mirror detection with the visual chirality cue. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022).
DOI: Google ScholarCross Ref
- [42] . 2021. Night-time scene parsing with a large real dataset. IEEE Transactions on Image Processing 30 (2021), 9085–9098.Google Scholar
Digital Library
- [43] . 2017. A stagewise refinement model for detecting salient objects in images. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [44] . 2020. F3Net: Fusion, feedback and focus for salient object detection. In Proceedings of the AAAI.Google Scholar
Cross Ref
- [45] . 2019. Cascaded partial decoder for fast and accurate salient object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [46] . 2019. Stacked cross refinement network for edge-aware salient object detection. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [47] . 2019. Structured modeling of joint deep feature and prediction refinement for salient object detection. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [48] . 2016. Camouflage performance analysis and evaluation framework based on features fusion. Multimedia Tools and Applications 75, 7 (2016), 4065–4082.Google Scholar
Digital Library
- [49] . 2013. Saliency detection via graph-based manifold ranking. In Proceedings of the CVPR.Google Scholar
Digital Library
- [50] . 2021. Learning with noisy labels for robust point cloud segmentation. In Proceedings of the ICCV (2021).Google Scholar
- [51] . 2011. Detection of the mobile object with camouflage color under dynamic background based on optical flow. Procedia Engineering 15 (2011), 2201–2205.
DOI: Google ScholarCross Ref
- [52] . 2020. Deep camouflage images. In Proceedings of the AAAI.Google Scholar
Cross Ref
- [53] . 2018. Progressive attention guided recurrent network for salient object detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [54] . 2017. Pyramid scene parsing network. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [55] . 2019. EGNet: Edge guidance network for salient object detection. In Proceedings of the ICCV.Google Scholar
Cross Ref
- [56] . 2019. Pyramid feature attention network for saliency detection. In Proceedings of the ICCV. 3085–3094.Google Scholar
Cross Ref
- [57] . 2019. Pyramid feature attention network for saliency detection. In Proceedings of the CVPR.Google Scholar
Cross Ref
- [58] . 2020. Suppress and balance: A simple gated network for salient object detection. In Proceedings of the ECCV.Google Scholar
Digital Library
- [59] . 2019. UNet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging 39, 6 (2019), 1856–1867.Google Scholar
- [60] . 2014. Saliency optimization from robust background detection. In Proceedings of the CVPR.Google Scholar
Digital Library
- [61] . 2020. Delving deeper into anti-aliasing in ConvNets. In Proceedings of the BMVC.Google Scholar
Index Terms
Frequency-aware Camouflaged Object Detection
Recommendations
Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
MMAsia '21: ACM Multimedia AsiaThis paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target object directly while outputting ambiguous camouflaged boundaries. On the ...
A Bayesian Approach to Camouflaged Moving Object Detection
Moving object detection is about foreground and background separation based on motion detection. Detecting moving objects from similarly colored background (known as camouflage problem) has been a long-standing open question in this field. Discriminative ...
Attention-induced semantic and boundary interaction network for camouflaged object detection
AbstractThe high intrinsic similarity between camouflaged objects and the background makes camouflaged object detection (COD) more challenging than traditional salient object detection (SOD). Existing deep-learning methods often fall into the ...
Highlights- A novel Camouflaged Object Detection (COD) framework that utilizes an attention-induced approach to enable semantic location and boundary information is ...






Comments