Abstract In the detection of camouflaged object, it is difficult to segment camouflaged object accurately due to the high similarity between appearance and backgrounds. In context-aware cross-level fusion network, the high-level semantic information is diluted and lost when it is transmitted to the shallow network fusion, resulting in the reduction of accuracy. Aiming at the problem, an camouflaged object detection(COD) network based on global multi-scale feature fusion(GMF2Net) is proposed. Firstly, the global enhanced fusion module(GEFM) is designed to capture the context information at different scales, and then the high-level semantic information is transmitted to the shallow network through different fusion enhanced branches to reduce the feature loss during multi-scale fusion. The location capture mechanism is designed in the high-level network to extract and refine the location of the camouflaged object, and feature extraction and fusion for high-resolution images are carried out in shallow network to enhance high-resolution feature details. Experiments on three benchmark datasets show that GMF2Net produces better performance.
Corresponding Authors:
ZHANG Guangjian, master, associate professor. His research interests include intelligent robot and system and intelligent system and application.
About author:: TONG Xuwei, master student. His research interests include image processing and machine learning.
[1] FAN D P, JI G P, ZHOU T, et al. PraNet: Parallel Reverse Attention Network for Polyp Segmentation // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2020: 263-273. [2] JI G P, CHOU Y C, FAN D P, et al. Progressively Normalized Self-Attention Network for Video Polyp Segmentation // Proc of the International Conference on Medical Image Computing and Compu-ter-Assisted Intervention. Berlin, Germany: Springer, 2021: 142-152. [3] AMIT S N K B, SHIRAISHI S, INOSHITA T, et al. Analysis of Satellite Images for Disaster Detection // Proc of the IEEE International Geoscience and Remote Sensing Symposium. Washington, USA: IEEE, 2016: 5189-5192. [4] YI D W, SU J Y, CHEN W H. Locust Recognition and Detection via Aggregate Channel Features // Proc of the 2nd UK-RAS Confe-rence for PhD Students and Early-Career Researches on "Embedded Intelligence". Leicester, UK: UK-RAS Network, 2019: 112-115. [5] GE S M, JIN X, YE Q T, et al. Image Editing by Object-Aware Optimal Boundary Searching and Mixed-Domain Composition. Computational Visual Media, 2018, 4(1): 71-82. [6] PAN Y X, CHEN Y W, FU Q, et al. Study on the Camouflaged Target Detection Method Based on 3D Convexity. Modern Applied Science, 2011, 5(4): 152-157. [7] YAN J N, LE T N, NGUYEN K D, et al. MirrorNet: Bio-Inspired Camouflaged Object Segmentation. IEEE Access, 2021, 9: 43290-43300. [8] LI A X, ZHANG J, LÜ Y Q, et al. Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 10066-10076. [9] YANG F, ZHAI Q, LI X, et al. Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 4126-4135. [10] JI G P, ZHU L, ZHUGE M C, et al. Fast Camouflaged Object Detection via Edge-Based Reversible Re-calibration Network. Pattern Recognition, 2022, 123. DOI: 10.1016/j.patcog.2021.108414. [11] MEI H Y, JI G P, WEI Z Q, et al. Camouflaged Object Segmentation with Distraction Mining // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 8768-8777. [12] FAN D P, JI G P, SUN G L, et al. Camouflaged Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2020: 2774-2784. [13] SUN Y J, CHEN G, ZHOU T, et al. Context-Aware Cross-Level Fusion Network for Camouflaged Object Detection // Proc of the 30th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2021: 1025-1031. [14] GUO D, LI K, ZHA Z J, et al. DADNet: Dilated-Attention-Deformable ConvNet for Crowd Counting // Proc of the 27th ACM International Conference on Multimedia. New York, USA: ACM, 2019: 1823-1832. [15] LI K, GUO D, WANG M. Proposal-Free Video Grounding with Contextual Pyramid Network. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(3): 1902-1910. [16] GAO S H, CHENG M M, ZHAO K, et al. Res2Net: A New Multi-scale Backbone Architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662. [17] ZHAO H S, SHI J P, QI X J, et al. Pyramid Scene Parsing Network // Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2017: 6230-6239. [18] LIU S T, HUANG D, WANG Y H. Receptive Field Block Net for Accurate and Fast Object Detection // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 404-419. [19] WEI J, WANG S H, HUANG Q M. F3Net: Fusion, Feedback and Focus for Salient Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 2020,34(7): 12321-12328. [20] LI W J, ZHANG Z Y, WANG X J, et al. AdaX: Adaptive Gradient Descent with Exponential Long Term Memory[C/OL].[2022-07-20]. https://arxiv.org/pdf/2004.09740.pdf. [21] LE T N, NGUYEN T V, NIE Z L, et al. Anabranch Network for Camouflaged Object Segmentation. Computer Vision and Image Understanding, 2019, 184: 45-56. [22] 范登平,季葛鹏,秦雪彬,等.认知规律启发的物体分割评价标准及损失函数.中国科学(信息科学), 2021, 51(9): 1475-1489. (FAN D P, JI G P, QIN X B, et al. Cognitive Vision Inspired Object Segmentation Metric and Loss Function. Scientia Sinica(Informationis), 2021, 51(9): 1475-1489.) [23] FAN D P, CHENG M M, LIU Y, et al. Structure-Measure: A New Way to Evaluate Foreground Maps // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 4558-4567. [24] MARGOLIN R, ZELNIK-MANOR L, TAL A. How to Evaluate Foreground Maps // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 248-255. [25] PERAZZI F, KRÄHENBÜHL P, PRITCH Y, et al. Saliency Filters: Contrast Based Filtering for Salient Region Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 733-740. [26] LIU N, HAN J W, YANG M H. PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 3089-3098. [27] LIU J J, HOU Q B, CHENG M M, et al. A Simple Pooling-Based Design for Real-Time Salient Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 3912-3921. [28] QIN X B, ZHANG Z C, HUANG C Y, et al. BASNet: Boundary-Aware Salient Object Detection // Proc of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 7471-7481. [29] ZHAO J X, LIU J J, FAN D P, et al. EGNet: Edge Guidance Network for Salient Object Detection // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 8778-8787. [30] ZHAI Q, LI X, YANG F, et al. Mutual Graph Learning for Camouflaged Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 12992-13002. [31] LÜ Y Q, ZHANG J, DAI Y C, et al. Simultaneously Localize, Segment and Rank the Camouflaged Objects // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 11586-11596.
2022, Vol. 35 
