水下顯著物體偵測（Underwater Salient Object Detection, USOD）因色彩衰減、低對比度與光散射等因素而極具挑戰性，這些因素會劣化物體外觀並模糊物體邊界。現有方法多仰賴影像復原或輔助線索，而其中的誤差可能進一步傳遞至顯著性預測。雖然近期基於 SAM 的方法利用預訓練基礎模型特徵來提升穩健性，但仍未明確處理邊界模糊的問題。因此，我們提出 EG-SAM，一個將跨任務再校準（cross-task recalibration）引入 SAM 以用於 USOD 的邊緣引導雙分支適應框架。

邊界分支與顯著性分支共享凍結的 SAM 主幹網路，但各自使用獨立的 LoRA、Adapter 與解碼器模組進行任務專屬學習。邊界分支透過邊界通道引導區塊（Boundary Channel Guidance Blocks）擷取具邊界感知的引導資訊，並經由邊界引導顯著性再校準區塊（Boundary-guided Saliency Recalibration Blocks）傳遞至顯著性分支。透過跨任務重參數化（cross-task re-parameterization），該引導資訊可自適應地再校準顯著性特徵，在保留任務專屬表徵的同時強化邊界感知能力。於公開基準上的實驗結果顯示，EG-SAM 在 USOD 與海洋生物分割任務上達到具競爭力或更優的效能；而在陸上顯著物體偵測與偽裝物體偵測上的評估亦展現出良好的泛化能力。

Underwater salient object detection (USOD) remains challenging due to color attenuation, low contrast, and light scattering, which degrade object appearance and obscure object boundaries. Existing methods often rely on image restoration or auxiliary cues, whose errors may propagate to saliency predictions. Although recent SAM-based methods exploit pretrained foundation features to improve robustness, they do not explicitly address blurred boundaries. We therefore propose EG-SAM, an edge-guided dual-branch adaptation framework that introduces cross-task recalibration into SAM for USOD.

The boundary and saliency branches share a frozen SAM backbone but use independent LoRA, Adapter, and decoder modules for task-specific learning. The boundary branch uses Boundary Channel Guidance Blocks to extract boundary-aware guidance, which is transferred to the saliency branch through Boundary-guided Saliency Recalibration Blocks. Through cross-task re-parameterization, the guidance adaptively recalibrates saliency features, enhancing boundary perception while preserving task-specific representations. Experiments on public benchmarks show that EG-SAM achieves competitive or superior performance in USOD and marine animal segmentation, while evaluations on terrestrial salient and camouflaged object detection demonstrate strong generalization.

[1] Pingping Zhang, Tianyu Yan, Yang Liu, and Huchuan Lu. “Fantastic animals and where to find them: Segment any marine animal with dual sam.” In: CVPR. 2024, pp. 2578–2587 (cit. pp. 1, 2, 6, 9, 22, 23, 25).
[2] Yiwen Liu, Xiaoyu Zhang, Jinchao Zhu, et al. “HDANet: Enhancing Underwater Salient Object Detection With Physics-Inspired Multimodal Joint Learning.” In: IEEE TGRS 63 (2025), pp. 1–14 (cit. pp. 1, 2, 5, 19, 25).
[3] Laurent Itti, Christof Koch, and Ernst Niebur. “A model of saliency-based visual attention for rapid scene analysis.” In: IEEE TPAMI 20.11 (1998), pp. 1254–1259 (cit. pp. 1, 3, 25).
[4] Filiz Gurkan, Llukman Cerkezi, Ozgun Cirakman, and Bilge Gunsel. “TDIOT: Target-driven inference for deep video object tracking.” In: IEEE TIP 30 (2021), pp. 7938–7951 (cit. p. 1).
[5] Zongjian Zhang, Qiang Wu, Yang Wang, and Fang Chen. “Exploring pairwise relationships adaptively from linguistic context in image captioning.” In: IEEE TMM 24 (2021), pp. 3101–3113 (cit. p. 1).
[6] Wenguan Wang, Shuyang Zhao, Jianbing Shen, Steven CH Hoi, and Ali Borji. “Salient object detection with pyramid attention and salient edges.” In: CVPR. 2019, pp. 1448–1457 (cit. p. 1).
[7] Lin Hong, Xin Wang, Gan Zhang, and Ming Zhao. “USOD10K: A New Benchmark Dataset for Underwater Salient Object Detection.” In: IEEE TIP 34 (2025), pp. 1602–1615 (cit. pp. 1, 3, 4, 19, 23, 25).
[8] Zhen Cui, Junfeng Wu, Hong Yu, Yizhi Zhou, and Liang Liang. “Underwater image saliency detection based on improved histogram equalization.” In: International Conference of Pioneering Computer Scientists, Engineers and Educators. Springer. 2019, pp. 157–165 (cit. pp. 1, 3).
[9] Hui Feng, Xinghui Yin, Lizhong Xu, et al. “Underwater salient object detection jointly using improved spectral residual and Fuzzy c-Means.” In: Journal of Intelligent & Fuzzy Systems 37.1 (2019), pp. 329–339 (cit. pp. 1, 3).
[10] Zhe Chen, Hongmin Gao, Zhen Zhang, et al. “Underwater salient object detection by combining 2D and 3D visual features.” In: Neurocomputing 391 (2020), pp. 249–259 (cit. pp. 1, 3).
[11] Muwei Jian, Qiang Qi, Junyu Dong, Yilong Yin, and Kin-Man Lam. “Integrating QDWD with pattern distinctness and local contrast for underwater saliency detection.” In: Journal of visual communication and image representation 53 (2018), pp. 31–41 (cit. pp. 1, 3).
[12] Jianhui Jin, Qiuping Jiang, Qingyuan Wu, Binwei Xu, and Runmin Cong. “Underwater Salient Object Detection via Dual-Stage Self-Paced Learning and Depth Emphasis.” In: IEEE TCSVT 35.3 (2025), pp. 2147–2160 (cit. pp. 1, 4, 5, 25).
[13] Yan-Tsung Peng, Yu-Cheng Lin, Wen-Yi Peng, and Chen-Yu Liu. “Blurriness-guided underwater salient object detection and data augmentation.” In: IEEE J. Ocean. Eng. 49.3 (2024), pp. 1089–1103 (cit. pp. 1, 4).
[14] Tianyu Yan, Zifu Wan, Xinhao Deng, et al. “MAS-SAM: segment any marine animal with aggregated features.” In: IJCAI. 2024, pp. 6886–6894 (cit. pp. 1, 6, 9, 25).
[15] Alexander Kirillov, Eric Mintun, Nikhila Ravi, et al. “Segment anything.” In: ICCV. 2023, pp. 4015–4026 (cit. pp. 1, 5, 24, 25, 33).
[16] Zhiming Luo, Akshaya Mishra, Andrew Achkar, et al. “Non-local deep features for salient object detection.” In: CVPR. 2017, pp. 6609–6617 (cit. pp. 1, 7, 39).
[17] Xuebin Qin, Zichen Zhang, Chenyang Huang, et al. “Basnet: Boundary-aware salient object detection.” In: CVPR. 2019, pp. 7479–7489 (cit. pp. 1, 7, 14, 15, 25).
[18] Jia-Xing Zhao, Jiang-Jiang Liu, Deng-Ping Fan, et al. “EGNet: Edge guidance network for salient object detection.” In: ICCV. 2019, pp. 8779–8788 (cit. pp. 1, 7, 15, 19, 25).
[19] Jun Wei, Shuhui Wang, Zhe Wu, et al. “Label decoupling framework for salient object detection.” In: CVPR. 2020, pp. 13025–13034 (cit. pp. 1, 7, 25, 33).
[20] Zhirui Zhao, Changqun Xia, Chenxi Xie, and Jia Li. “Complementary trilateral decoder for fast and accurate salient object detection.” In: ACM MM. 2021, pp. 4967–4975 (cit. pp. 1, 7, 25).
[21] Md Jahidul Islam, Ruobing Wang, and Junaed Sattar. “SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robot.” In: Robot.: Sci. Syst. (RSS). 2022 (cit. pp. 3, 4, 20, 23, 25).
[22] Zhenqi Fu, Ruizhe Chen, Yue Huang, et al. “MASNet: A Robust Deep Marine Animal Segmentation Network.” In: IEEE J. Ocean. Eng. 49.3 (2024), pp. 1104–1115 (cit. pp. 4, 22, 24, 25).
[23] Tianrun Chen, Lanyun Zhu, Chaotao Deng, et al. “Sam-adapter: Adapting segment anything in underperformed scenes.” In: ICCVW . 2023, pp. 3367–3375 (cit. pp. 6, 25, 32, 33).
[24] Kaidong Zhang and Dong Liu. Customized Segment Anything Model for Medical Image Segmentation. 2023. arXiv: 2304.13785 (cit. p. 6).
[25] Yifan Gao, Wei Xia, Dingdu Hu, Wenkui Wang, and Xin Gao. “Desam: Decoupled segment anything model for generalizable medical image segmentation.” In: MICCAI. Springer. 2024, pp. 509–519 (cit. p. 6).
[26] Pingping Zhang, Tianyu Yan, Yuhao Wang, et al. “HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation.” In: IEEE TIP 35 (2026), pp. 3311–3323 (cit. pp. 6, 7, 25, 28).
[27] Yu-Cheng Chiu, Guan-Rong Chen, Zihao Chen, and Yan-Tsung Peng. “Abc-former: Auxiliary bimodal cross-domain transformer with interactive channel attention for white balance.” In: CVPR. 2025, pp. 21258–21266 (cit. pp. 7, 11).
[28] Edward J. Hu, Yelong Shen, Phillip Wallis, et al. “LoRA: Low-Rank Adaptation of Large Language Models.” In: ICLR. 2022 (cit. p. 9).
[29] Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, et al. “Parameter-efficient transfer learning for NLP.” In: ICML. PMLR. 2019, pp. 2790–2799 (cit. p. 9).
[30] Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. “V-net: Fully convolutional neural networks for volumetric medical image segmentation.” In: 2016 fourth international conference on 3D vision (3DV). IEEE. 2016, pp. 565–571 (cit. p. 15).
[31] René Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. “Vision transformers for dense prediction.” In: ICCV. 2021, pp. 12179–12188 (cit. p. 19).
[32] Lin Li, Eric Rigall, Junyu Dong, and Geng Chen. “MAS3K: An open dataset for marine animal segmentation.” In: International Symposium on Benchmarking, Measuring and Optimization. Springer. 2020, pp. 194–212 (cit. pp. 21, 23).
[33] Paulo Drews-Jr, Isadora de Souza, Igor P Maurell, Eglen V Protas, and Silvia S C. Botelho. “Underwater image segmentation in the wild using deep learning.” In: Journal of the Brazilian Computer Society 27.1 (2021), p. 12 (cit. pp. 22, 24).
[34] Md Jahidul Islam, Peigen Luo, and Junaed Sattar. “Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception.” In: Robot.: Sci. Syst. (RSS). 2020 (cit. pp. 23, 24).
[35] Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, et al. “SAM 2: Segment Anything in Images and Videos.” In: ICLR. 2025 (cit. p. 24).
[36] Ilya Loshchilov and Frank Hutter. “Decoupled Weight Decay Regularization.” In: ICLR. 2019 (cit. p. 24).
[37] Deng-Ping Fan, Ming-Ming Cheng, Yun Liu, Tao Li, and Ali Borji. “Structure-measure: A new way to evaluate foreground maps.” In: ICCV. 2017, pp. 4548–4557 (cit. p. 24).
[38] Deng-Ping Fan, Cheng Gong, Yang Cao, et al. “Enhanced-alignment Measure for Binary Foreground Map Evaluation.” In: IJCAI. 2018, pp. 698–704 (cit. p. 24).
[39] Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan, and Ming-Hsuan Yang. “Saliency detection via graph-based manifold ranking.” In: CVPR. 2013, pp. 3166–3173 (cit. pp. 24, 32).
[40] Federico Perazzi, Philipp Krähenbühl, Yael Pritch, and Alexander Hornung. “Saliency filters: Contrast based filtering for salient region detection.” In: CVPR. IEEE. 2012, pp. 733–740 (cit. p. 24).
[41] Bowen Cheng, Ross Girshick, Piotr Dollár, Alexander C Berg, and Alexander Kirillov. “Boundary IoU: Improving object-centric image segmentation evaluation.” In: CVPR. 2021, pp. 15334–15342 (cit. p. 24).
[42] Ran Margolin, Lihi Zelnik-Manor, and Ayellet Tal. “How to evaluate foreground maps?” In: CVPR. 2014, pp. 248–255 (cit. p. 24).
[43] Jun Wei, Shuhui Wang, and Qingming Huang. “F3 Net: fusion, feedback and focus for salient object detection.” In: AAAI. 2020, pp. 12321–12328 (cit. pp. 25, 33).
[44] Mingcan Ma, Changqun Xia, and Jia Li. “Pyramidal feature shrinking for salient object detection.” In: AAAI. 2021, pp. 2311–2318 (cit. p. 25).
[45] Sheng Yang, Weisi Lin, Guosheng Lin, Qiuping Jiang, and Zichuan Liu. “Progressive self-guided loss for salient object detection.” In: IEEE TIP 30 (2021), pp. 8426–8438 (cit. p. 25).
[46] Ming-Ming Cheng, Shang-Hua Gao, Ali Borji, et al. “A highly efficient model to study the semantics of salient object detection.” In: IEEE TPAMI 44.11 (2021), pp. 8006–8021 (cit. p. 25).
[47] Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, and Junwei Han. “Visual saliency transformer.” In: ICCV. 2021, pp. 4722–4732 (cit. pp. 25, 33).
[48] Nian Liu, Ni Zhang, Ling Shao, and Junwei Han. “Learning selective mutual attention and contrast for RGB-D saliency detection.” In: IEEE TPAMI 44.12 (2021), pp. 9026–9042 (cit. p. 25).
[49] Binwei Xu, Haoran Liang, Ronghua Liang, and Peng Chen. “Locate globally, segment locally: A progressive architecture with knowledge review network for salient object detection.” In: AAAI. 2021, pp. 3004–3012 (cit. p. 25).
[50] Wei Ji, Jingjing Li, Shuang Yu, et al. “Calibrated RGB-D salient object detection.” In: CVPR. 2021, pp. 9471–9481 (cit. p. 25).
[51] Tao Zhou, Huazhu Fu, Geng Chen, et al. “Specificity-preserving RGB-D saliency detection.” In: ICCV. 2021, pp. 4681–4691 (cit. p. 25).
[52] Gongyang Li, Zhi Liu, Minyu Chen, et al. “Hierarchical alternate interaction network for RGB-D salient object detection.” In: IEEE TIP 30 (2021), pp. 3528–3542 (cit. p. 25).
[53] Zhengyi Liu, Yuan Wang, Zhengzheng Tu, Yun Xiao, and Bin Tang. “TriTransNet: RGB-D salient object detection with a triplet transformer embedding network.” In: ACM MM. 2021, pp. 4481–4490 (cit. p. 25).
[54] Deng-Ping Fan, Zheng Lin, Zhao Zhang, Menglong Zhu, and Ming-Ming Cheng. “Rethinking RGB-D salient object detection: Models, data sets, and large-scale benchmarks.” In: IEEE TNNLS 32.5 (2020), pp. 2075–2089 (cit. p. 25).
[55] Wenbo Zhang, Yao Jiang, Keren Fu, and Qijun Zhao. “BTS-Net: Bi-Directional Transfer-and-Selection Network for RGB-D Salient Object Detection.” In: ICME. 2021, pp. 1–6 (cit. p. 25).
[56] Chen Zhang, Runmin Cong, Qinwei Lin, et al. “Cross-modality discrepant interaction network for RGB-D salient object detection.” In: ACM MM. 2021, pp. 2094–2102 (cit. p. 25).
[57] Yongri Piao, Jian Wang, Miao Zhang, and Huchuan Lu. “MFNet: Multi-filter directive network for weakly supervised salient object detection.” In: ICCV. 2021, pp. 4136–4145 (cit. p. 25).
[58] Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. “Unet++: A nested u-net architecture for medical image segmentation.” In: International workshop on deep learning in medical image analysis. Springer. 2018, pp. 3–11 (cit. p. 25).
[59] Ting Zhao and Xiangqian Wu. “Pyramid feature attention network for saliency detection.” In: CVPR. 2019, pp. 3085–3094 (cit. p. 25).
[60] Zhe Wu, Li Su, and Qingming Huang. “Stacked cross refinement network for edge-aware salient object detection.” In: ICCV. 2019, pp. 7264–7273 (cit. p. 25).
[61] Xuebin Qin, Zichen Zhang, Chenyang Huang, et al. “U2-Net: Going deeper with nested U-structure for salient object detection.” In: PR 106 (2020), p. 107404 (cit. p. 25).
[62] Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, et al. “Camouflaged object detection.” In: CVPR. 2020, pp. 2777–2787 (cit. pp. 25, 32, 33).
[63] Haiyang Mei, Ge-Peng Ji, Ziqi Wei, et al. “Camouflaged object segmentation with distraction mining.” In: CVPR. 2021, pp. 8772–8781 (cit. pp. 25, 33).
[64] Yunqiu Lv, Jing Zhang, Yuchao Dai, et al. “Simultaneously localize, segment and rank the camouflaged objects.” In: CVPR. 2021, pp. 11591–11601 (cit. pp. 25, 33).
[65] Yujia Sun, Geng Chen, Tao Zhou, Yi Zhang, and Nian Liu. “Context-aware Cross-level Fusion Network for Camouflaged Object Detection.” In: IJCAI. 2021, pp. 1025–1031 (cit. p. 25).
[66] Lin Li, Bo Dong, Eric Rigall, et al. “Marine animal segmentation.” In: IEEE TCSVT 32.4 (2021), pp. 2303–2314 (cit. p. 25).
[67] Jiawei Liu, Jing Zhang, and Nick Barnes. “Modeling aleatoric uncertainty for camouflaged object detection.” In: WACV. 2022, pp. 1445–1454 (cit. p. 25).
[68] Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, and Huchuan Lu. “Zoom in and out: A mixed-scale triplet network for camouflaged object detection.” In: CVPR. 2022, pp. 2160–2170 (cit. p. 25).
[69] Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, et al. “Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers.” In: CVPR. 2021, pp. 6881–6890 (cit. p. 25).
[70] Jieneng Chen, Yongyi Lu, Qihang Yu, et al. TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. 2021. arXiv: 2102.04306 (cit. p. 25).
[71] Along He, Kai Wang, Tao Li, et al. “H2former: An efficient hierarchical hybrid transformer for medical image segmentation.” In: IEEE TMI 42.9 (2023), pp. 2763–2775 (cit. p. 25).
[72] Tianrun Chen, Ankang Lu, Lanyun Zhu, et al. SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More. 2024. arXiv: 2408.04579 (cit. p. 25).
[73] Lijun Wang, Huchuan Lu, Yifan Wang, et al. “Learning to detect salient objects with image-level supervision.” In: CVPR. 2017, pp. 136–145 (cit. p. 32).
[74] Guanbin Li and Yizhou Yu. “Visual saliency based on multiscale deep features.” In: CVPR. 2015, pp. 5455–5463 (cit. p. 32).
[75] Yin Li, Xiaodi Hou, Christof Koch, James M Rehg, and Alan L Yuille. “The secrets of salient object segmentation.” In: CVPR. 2014, pp. 280–287 (cit. p. 32).
[76] Qiong Yan, Li Xu, Jianping Shi, and Jiaya Jia. “Hierarchical saliency detection.” In: CVPR. 2013, pp. 1155–1162 (cit. p. 32).
[77] Guangyu Ren, Hengyan Liu, Michalis Lazarou, and Tania Stathaki. “Multi-modal Segment Anything Model for Camouflaged Scene Segmentation.” In: ICCV. 2025, pp. 19882–19892 (cit. pp. 32, 33).
[78] Trung-Nghia Le, Tam V Nguyen, Zhongliang Nie, Minh-Triet Tran, and Akihiro Sugimoto. “Anabranch network for camouflaged object segmentation.” In: Computer vision and image understanding 184 (2019), pp. 45–56 (cit. p. 32).
[79] Przemysław Skurowski, Hassan Abdulameer, Jakub Błaszczyk, et al. “Animal camouflage analysis: Chameleon database.” In: Unpublished manuscript 2.6 (2018), p. 7 (cit. p. 32).
[80] Shixuan Gao, Pingping Zhang, Tianyu Yan, and Huchuan Lu. “Multi-scale and detail-enhanced segment anything model for salient object detection.” In: ACM MM. 2024, pp. 9894–9903 (cit. pp. 32, 33).
[81] Runmin Cong, Zhiyang Chen, Hao Fang, Sam Kwong, and Wei Zhang. “Breaking Barriers, Localizing Saliency: A Large-Scale Benchmark and Baseline for Condition-Constrained Salient Object Detection.” In: IEEE TPAMI 48.4 (2026), pp. 4167–4183 (cit. pp. 32, 33).
[82] Sina Mohammadi, Mehrdad Noori, Ali Bahri, Sina Ghofrani Majelan, and Mohammad Havaei. “CAGNet: Content-aware guidance for salient object detection.” In: PR 103 (2020), p. 107303 (cit. p. 33).
[83] Jiang-Jiang Liu, Qibin Hou, and Ming-Ming Cheng. “Dynamic feature integration for simultaneous detection of salient object, edge, and skeleton.” In: IEEE TIP 29 (2020), pp. 8652–8667 (cit. p. 33).
[84] Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, and Lei Zhang. “Suppress and balance: A simple gated network for salient object detection.” In: ECCV . Springer. 2020, pp. 35–51 (cit. p. 33).
[85] Youwei Pang, Xiaoqi Zhao, Lihe Zhang, and Huchuan Lu. “Multi-scale interactive network for salient object detection.” In: CVPR. 2020, pp. 9413–9422 (cit. p. 33).
[86] Min Seok Lee, WooSeok Shin, and Sung Won Han. “Tracer: Extreme attention guided salient object tracing network (student abstract).” In: AAAI. 2022, pp. 12993–12994 (cit. p. 33).
[87] Mingchen Zhuge, Deng-Ping Fan, Nian Liu, et al. “Salient object detection via integrity learning.” In: IEEE TPAMI 45.3 (2022), pp. 3738–3752 (cit. p. 33).
[88] Mingcan Ma, Changqun Xia, Chenxi Xie, Xiaowu Chen, and Jia Li. “Boosting broader receptive fields for salient object detection.” In: IEEE TIP 32 (2023), pp. 1026–1038 (cit. p. 33).
[89] Yi Wang, Ruili Wang, Xin Fan, Tianzhu Wang, and Xiangjian He. “Pixels, regions, and objects: Multiple enhancement for salient object detection.” In: CVPR. 2023, pp. 10031–10040 (cit. p. 33).
[90] Yi Ke Yun and Weisi Lin. SelfReformer: Self-Refined Network with Transformer for Salient Object Detection. 2022. arXiv: 2205.11283 (cit. p. 33).
[91] Jiayi Zhu, Xuebin Qin, and Abdulmotaleb Elsaddik. “Dc-net: Divide-and-conquer for salient object detection.” In: PR 157 (2025), p. 110903 (cit. p. 33).
[92] Aixuan Li, Jing Zhang, Yunqiu Lv, et al. “Uncertainty-aware joint salient object and camouflaged object detection.” In: CVPR. 2021, pp. 10071–10081 (cit. p. 33).
[93] Jiaying Lin, Xin Tan, Ke Xu, Lizhuang Ma, and Rynson WH Lau. “Frequency-aware camouflaged object detection.” In: ACM TOMM 19.2 (2023), pp. 1–16 (cit. p. 33).
[94] Zhou Huang, Hang Dai, Tian-Zhu Xiang, et al. “Feature shrinkage pyramid for camouflaged object detection with transformers.” In: CVPR. 2023, pp. 5557–5566 (cit. p. 33).