{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:17:54Z","timestamp":1772907474526,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62121001"],"award-info":[{"award-number":["62121001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Hyperspectral anomaly detection (HAD) is of great interest for unknown exploration. Existing methods only focus on local similarity, which may show limitations in detection performance. To cope with this problem, we propose a relationship attention-guided unsupervised learning with convolutional autoencoders (CAEs) for HAD, called RANet. First, instead of only focusing on the local similarity, RANet, for the first time, pays attention to topological similarity by leveraging the graph attention network (GAT) to capture deep topological relationships embedded in a customized incidence matrix from absolutely unlabeled data mixed with anomalies. Notably, the attention intensity of GAT is self-adaptively controlled by adjacency reconstruction ability, which can effectively reduce human intervention. Next, we adopt an unsupervised CAE to jointly learn with the topological relationship attention to achieve satisfactory model performance. Finally, on the basis of background reconstruction, we detect anomalies by the reconstruction error. Extensive experiments on hyperspectral images (HSIs) demonstrate that our proposed RANet outperforms existing fully unsupervised methods.<\/jats:p>","DOI":"10.3390\/rs15235570","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T09:37:54Z","timestamp":1701337074000},"page":"5570","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["RANet: Relationship Attention for Hyperspectral Anomaly Detection"],"prefix":"10.3390","volume":"15","author":[{"given":"Yingzhao","family":"Shao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi\u2019an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi\u2019an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanle","family":"Wang","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"},{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Yang","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueli","family":"Ding","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingming","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology (Xi\u2019an), Xi\u2019an 710100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3574","DOI":"10.1109\/TIP.2014.2329767","article-title":"Hyperspectral image segmentation using a new spectral unmixing-based binary partition tree representation","volume":"23","author":"Veganzones","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1109\/TIP.2016.2542360","article-title":"Hyperspectral image super-resolution via non-negative structured sparse representation","volume":"25","author":"Dong","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1860","DOI":"10.1109\/TIP.2005.854479","article-title":"Super-resolution reconstruction of hyperspectral images","volume":"14","author":"Akgun","year":"2005","journal-title":"IEEE Trans. Image Process."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.1109\/TIP.2018.2884076","article-title":"Hyperreconnet: Joint coded aperture optimization and image reconstruction for compressive hyperspectral imaging","volume":"28","author":"Wang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1109\/TIP.2015.2496263","article-title":"Hyperspectral super-resolution of locally low rank images from complementary multisource data","volume":"25","author":"Veganzones","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_6","first-page":"4139","article-title":"Lren: Low-rank embedded network for sample-free hyperspectral anomaly detection","volume":"35","author":"Jiang","year":"2021","journal-title":"AAAI-AAAI Conf. Artif. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1259","DOI":"10.1109\/TIP.2017.2772836","article-title":"Semi-supervised deep learning using pseudo labels for hyperspectral image classification","volume":"27","author":"Wu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.1109\/TIP.2016.2545248","article-title":"Hyperspectral image target detection improvement based on total variation","volume":"25","author":"Yang","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/TIP.2015.2509258","article-title":"Nonparametric detection of nonlinearly mixed pixels and endmember estimation in hyperspectral images","volume":"25","author":"Imbiriba","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5345","DOI":"10.1109\/TIP.2016.2601268","article-title":"Beyond the sparsity-based target detector: A hybrid sparsity and statistics-based detector for hyperspectral images","volume":"25","author":"Du","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2148","DOI":"10.1109\/TIP.2014.2312616","article-title":"Residual component analysis of hyperspectral images\u2014Application to joint nonlinear unmixing and nonlinearity detection","volume":"23","author":"Altmann","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2307","DOI":"10.1109\/TGRS.2020.3005924","article-title":"Hyperspectral anomaly detection via image super-resolution processing and spatial correlation","volume":"59","author":"Li","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6995","DOI":"10.1109\/TGRS.2020.2978510","article-title":"Hyperspectral anomaly detection via locally enhanced low-rank prior","volume":"58","author":"Wang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8503","DOI":"10.1109\/TGRS.2020.2988385","article-title":"Hyperspectral anomaly detection using dual window density","volume":"58","author":"Tu","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3022","DOI":"10.1109\/TSP.2020.2991311","article-title":"Training data assisted anomaly detection of multi-pixel targets in hyperspectral imagery","volume":"68","author":"Liu","year":"2020","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4810","DOI":"10.1109\/TGRS.2019.2893116","article-title":"Similarity constrained convex nonnegative matrix factorization for hyperspectral anomaly detection","volume":"57","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MGRS.2018.2853555","article-title":"A review of the autoencoder and its variants: A comparative perspective from target recognition in synthetic-aperture radar images","volume":"6","author":"Dong","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1109\/29.60107","article-title":"Adaptive multiple-band cfar detection of an optical pattern with unknown spectral distribution","volume":"38","author":"Reed","year":"1990","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/LGRS.2013.2257670","article-title":"A locally adaptive background density estimator: An evolution for rx-based anomaly detectors","volume":"11","author":"Matteoli","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1109\/TGRS.2014.2343955","article-title":"Collaborative representation for hyperspectral anomaly detection","volume":"53","author":"Li","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2523","DOI":"10.1109\/JSTARS.2015.2437073","article-title":"Hyperspectral anomaly detection by the use of background joint sparse representation","volume":"8","author":"Li","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1109\/TGRS.2015.2479299","article-title":"A low-rank and sparse matrix decomposition-based mahalanobis distance method for hyperspectral anomaly detection","volume":"54","author":"Zhang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1990","DOI":"10.1109\/TGRS.2015.2493201","article-title":"Anomaly detection in hyperspectral images based on low-rank and sparse representation","volume":"54","author":"Xu","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1109\/JAS.2017.7510583","article-title":"Generative adversarial networks: Introduction and outlook","volume":"4","author":"Wang","year":"2017","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1109\/LGRS.2017.2657818","article-title":"Transferred deep learning for anomaly detection in hyperspectral imagery","volume":"14","author":"Li","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/TPAMI.2012.88","article-title":"Robust recovery of subspace structures by low-rank representation","volume":"35","author":"Liu","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abati, D., Porrello, A., Calderara, S., and Cucchiara, R. (2019, January 15\u201320). Latent space autoregression for novelty detection. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00057"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Park, H., Noh, J., and Ham, B. (2020, January 14\u201319). Learning memory-guided normality for anomaly detection. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Pang, G., Yan, C., Shen, C., Hengel, A.V., and Bai, X. (2020, January 14\u201319). Self-trained deep ordinal regression for end-to-end video anomaly detection. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01219"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.neunet.2019.08.012","article-title":"Spectral constraint adversarial autoencoders approach to feature representation in hyperspectral anomaly detection","volume":"119","author":"Xie","year":"2019","journal-title":"Neural Netw."},{"key":"ref_31","first-page":"5523613","article-title":"Dual-frequency autoencoder for anomaly detection in transformed hyperspectral imagery","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","first-page":"5512312","article-title":"Spectral distribution-aware estimation network for hyperspectral anomaly detection","volume":"60","author":"Xie","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","first-page":"1","article-title":"Auto-ad: Autonomous hyperspectral anomaly detection network based on fully convolutional autoencoder","volume":"60","author":"Wang","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6504","DOI":"10.1109\/TNNLS.2021.3082158","article-title":"Weakly supervised discriminative learning with spectral constrained generative adversarial network for hyperspectral anomaly detection","volume":"33","author":"Jiang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4666","DOI":"10.1109\/TGRS.2020.2965961","article-title":"Discriminative reconstruction constrained generative adversarial network for hyperspectral anomaly detection","volume":"58","author":"Jiang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"9553","DOI":"10.1109\/TGRS.2021.3049224","article-title":"Hyperspectral anomaly detection via deep plug-and-play denoising cnn regularization","volume":"59","author":"Fu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","unstructured":"Ma, J., Xie, W., Li, Y., and Fang, L. (2023). Bsdm: Background suppression diffusion model for hyperspectral anomaly detection. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TCYB.2022.3175771","article-title":"Learning tensor low-rank representation for hyperspectral anomaly detection","volume":"53","author":"Wang","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"11385","DOI":"10.1109\/TCYB.2021.3079247","article-title":"E2e-liade: End-to-end local invariant autoencoding density estimation model for anomaly target detection in hyperspectral image","volume":"52","author":"Jiang","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1093\/clinchem\/39.4.561","article-title":"Receiver-operating characteristic (roc) plots: A fundamental evaluation tool in clinical medicine","volume":"39","author":"Zweig","year":"1993","journal-title":"Clin. Chem."},{"key":"ref_41","unstructured":"Flach, P., Hern\u00e1ndezorallo, J., and Ferri, C. (July, January 28). A coherent interpretation of aucas a measure of aggregated classification performance. Proceedings of the 28th International Conference on Machine Learning (ICML-11), Bellevue, WA, USA."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1080\/00031305.1978.10479236","article-title":"Variation of box plots","volume":"32","author":"Mcgill","year":"1978","journal-title":"Am. Stat."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"4033","DOI":"10.1109\/TGRS.2019.2960391","article-title":"A subspace selection-based discriminative forest method for hyperspectral anomaly detection","volume":"58","author":"Chang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"4363","DOI":"10.1109\/TCYB.2020.2968750","article-title":"Low-rank and sparse decomposition with mixture of gaussian for hyperspectral anomaly detection","volume":"51","author":"Li","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1109\/TNNLS.2020.3038659","article-title":"Prior-based tensor approximation for anomaly detection in hyperspectral imagery","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1109\/TGRS.2018.2872590","article-title":"Hyperspectral anomaly detection via background and potential anomaly dictionaries construction","volume":"57","author":"Huyan","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5557","DOI":"10.1109\/TNNLS.2021.3071026","article-title":"Multipixel anomaly detection with unknown patterns for hyperspectral imagery","volume":"33","author":"Liu","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5570\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:34:34Z","timestamp":1760132074000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":47,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["rs15235570"],"URL":"https:\/\/doi.org\/10.3390\/rs15235570","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,30]]}}}