{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:10:04Z","timestamp":1777626604604,"version":"3.51.4"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"31","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272345"],"award-info":[{"award-number":["62272345"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s00521-023-08816-2","type":"journal-article","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T19:02:58Z","timestamp":1693854178000},"page":"23249-23264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MECPformer: multi-estimations complementary patch with CNN-transformers for weakly supervised semantic segmentation"],"prefix":"10.1007","volume":"35","author":[{"given":"Chunmeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5853-6778","authenticated-orcid":false,"given":"Guangyao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,4]]},"reference":[{"issue":"3","key":"8816_CR1","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng D, Haase-Sch\u00fctz C, Rosenbaum L, Hertlein H, Glaeser C, Timm F, Wiesbeck W, Dietmayer K (2020) Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans Intell Transp Syst 22(3):1341\u20131360","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"7","key":"8816_CR2","doi-asserted-by":"publisher","first-page":"4444","DOI":"10.1109\/TCSVT.2021.3121680","volume":"32","author":"X Weng","year":"2021","unstructured":"Weng X, Yan Y, Chen S, Xue J-H, Wang H (2021) Stage-aware feature alignment network for real-time semantic segmentation of street scenes. IEEE Trans Circ Syst Video Technol 32(7):4444\u20134459","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"8816_CR3","doi-asserted-by":"crossref","unstructured":"Lee J, Yi J, Shin C, Yoon S (2021) Bbam: bounding box attribution map for weakly supervised semantic and instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2643\u20132652","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"8816_CR4","doi-asserted-by":"crossref","unstructured":"Lin D, Dai J, Jia J, He K, Sun J (2016) Scribblesup: scribble-supervised convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3159\u20133167","DOI":"10.1109\/CVPR.2016.344"},{"key":"8816_CR5","doi-asserted-by":"crossref","unstructured":"Bearman A, Russakovsky O, Ferrari V, Fei-Fei L (2016) What\u2019s the point: semantic segmentation with point supervision. In: European conference on computer vision, pp 549\u2013565. Springer","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"8816_CR6","doi-asserted-by":"crossref","unstructured":"Ahn J, Kwak S (2018) Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4981\u20134990","DOI":"10.1109\/CVPR.2018.00523"},{"key":"8816_CR7","doi-asserted-by":"crossref","unstructured":"Lee S, Lee M, Lee J, Shim H (2021) Railroad is not a train: saliency as pseudo-pixel supervision for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 5495\u20135505","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"8816_CR8","doi-asserted-by":"crossref","unstructured":"Wu T, Huang J, Gao G, Wei X, Wei X, Luo X, Liu CH (2021) Embedded discriminative attention mechanism for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16765\u201316774","DOI":"10.1109\/CVPR46437.2021.01649"},{"key":"8816_CR9","doi-asserted-by":"crossref","unstructured":"Wei Y, Feng J, Liang X, Cheng M-M, Zhao Y, Yan S (2017) Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1568\u20131576","DOI":"10.1109\/CVPR.2017.687"},{"key":"8816_CR10","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Wang J, Liu W, Wang J (2018) Weakly-supervised semantic segmentation network with deep seeded region growing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7014\u20137023","DOI":"10.1109\/CVPR.2018.00733"},{"key":"8816_CR11","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921\u20132929","DOI":"10.1109\/CVPR.2016.319"},{"key":"8816_CR12","doi-asserted-by":"crossref","unstructured":"Xu L, Ouyang W, Bennamoun M, Boussaid F, Xu D (2022) Multi-class token transformer for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4310\u20134319","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"8816_CR13","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"8816_CR14","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) Segformer: simple and efficient design for semantic segmentation with transformers. Adv Neural Inf Process Syst 34:12077","journal-title":"Adv Neural Inf Process Syst"},{"key":"8816_CR15","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Fan D-P, Song K, Liang D, Lu T, Luo P, Shao L (2021) Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 568\u2013578","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"8816_CR16","doi-asserted-by":"crossref","unstructured":"Peng Z, Huang W, Gu S, Xie L, Wang Y, Jiao J, Ye Q (2021) Conformer: local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 367\u2013376","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"8816_CR17","doi-asserted-by":"crossref","unstructured":"Li K, Wang Y, Zhang J, Gao P, Song G, Liu Y, Li H, Qiao Y (2022) Uniformer: unifying convolution and self-attention for visual recognition. arXiv preprint arXiv:2201.09450","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"8816_CR18","doi-asserted-by":"crossref","unstructured":"Li R, Mai Z, Trabelsi C, Zhang Z, Jang J, Sanner S (2022) Transcam: transformer attention-based cam refinement for weakly supervised semantic segmentation. arXiv preprint arXiv:2203.07239","DOI":"10.1016\/j.jvcir.2023.103800"},{"issue":"1","key":"8816_CR19","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami S, Van Gool L, Williams CK, Winn J, Zisserman A (2015) The pascal visual object classes challenge: a retrospective. Int J Comput Vis 111(1):98\u2013136","journal-title":"Int J Comput Vis"},{"key":"8816_CR20","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"8816_CR21","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8816_CR22","unstructured":"Hou Q, Jiang P, Wei Y, Cheng M-M (2018) Self-erasing network for integral object attention. Adv Neural Inf Process Syst31"},{"key":"8816_CR23","doi-asserted-by":"crossref","unstructured":"Wei Y, Xiao H, Shi H, Jie Z, Feng J, Huang TS (2018) Revisiting dilated convolution: a simple approach for weakly-and semi-supervised semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7268\u20137277","DOI":"10.1109\/CVPR.2018.00759"},{"key":"8816_CR24","doi-asserted-by":"crossref","unstructured":"Lee J, Kim E, Lee S, Lee J, Yoon S (2019) Ficklenet: weakly and semi-supervised semantic image segmentation using stochastic inference. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5267\u20135276","DOI":"10.1109\/CVPR.2019.00541"},{"key":"8816_CR25","doi-asserted-by":"crossref","unstructured":"Jiang P-T, Hou Q, Cao Y, Cheng M-M, Wei Y, Xiong H-K (2019) Integral object mining via online attention accumulation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2070\u20132079","DOI":"10.1109\/ICCV.2019.00216"},{"key":"8816_CR26","doi-asserted-by":"crossref","unstructured":"Chang Y-T, Wang Q, Hung W-C, Piramuthu R, Tsai Y-H, Yang M-H (2020) Weakly-supervised semantic segmentation via sub-category exploration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8991\u20139000","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"8816_CR27","doi-asserted-by":"crossref","unstructured":"Chen Q, Yang L, Lai J-H, Xie X (2022) Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4288\u20134298","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"8816_CR28","doi-asserted-by":"crossref","unstructured":"Sun G, Wang W, Dai J, Van\u00a0Gool L (2020) Mining cross-image semantics for weakly supervised semantic segmentation. In: European conference on computer vision, pp 347\u2013365. Springer","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"8816_CR29","doi-asserted-by":"crossref","unstructured":"Kumar\u00a0Singh K, Jae\u00a0Lee Y (2017) Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: Proceedings of the ieee international conference on computer vision, pp 3524\u20133533","DOI":"10.1109\/ICCV.2017.381"},{"key":"8816_CR30","doi-asserted-by":"crossref","unstructured":"Zhang F, Gu C, Zhang C, Dai Y (2021) Complementary patch for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7242\u20137251","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"8816_CR31","doi-asserted-by":"crossref","unstructured":"Ranftl R, Bochkovskiy A, Koltun V (2021) Vision transformers for dense prediction. In: Proceedings of the IEEE\/cvf international conference on computer vision, pp 12179\u201312188","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"8816_CR32","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C (2021) Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6836\u20136846","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"8816_CR33","doi-asserted-by":"crossref","unstructured":"Ru L, Zhan Y, Yu B, Du B (2022) Learning affinity from attention: End-to-end weakly-supervised semantic segmentation with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16846\u201316855","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"8816_CR34","unstructured":"Ke T-W, Hwang J-J, Yu SX (2021) Universal weakly supervised segmentation by pixel-to-segment contrastive learning. arXiv preprint arXiv:2105.00957"},{"key":"8816_CR35","doi-asserted-by":"crossref","unstructured":"Kolesnikov A, Lampert CH (2016) Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In: European conference on computer vision, pp 695\u2013711. Springer","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"8816_CR36","doi-asserted-by":"crossref","unstructured":"Zhang B, Xiao J, Wei Y, Sun M, Huang K (2020) Reliability does matter: an end-to-end weakly supervised semantic segmentation approach. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 12765\u201312772","DOI":"10.1609\/aaai.v34i07.6971"},{"key":"8816_CR37","doi-asserted-by":"crossref","unstructured":"Kim B, Han S, Kim J (2021) Discriminative region suppression for weakly-supervised semantic segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 1754\u20131761","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"8816_CR38","doi-asserted-by":"crossref","unstructured":"Yao Y, Chen T, Xie G-S, Zhang C, Shen F, Wu Q, Tang Z, Zhang J (2021) Non-salient region object mining for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2623\u20132632","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"8816_CR39","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhang J, Kan M, Shan S, Chen X (2019) Self-supervised scale equivariant network for weakly supervised semantic segmentation. arXiv preprint arXiv:1909.03714","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"8816_CR40","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhang J, Kan M, Shan S, Chen X (2020) Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12275\u201312284","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"8816_CR41","doi-asserted-by":"crossref","unstructured":"Fan J, Zhang Z, Tan T, Song C, Xiao J (2020) Cian: cross-image affinity net for weakly supervised semantic segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 10762\u201310769","DOI":"10.1609\/aaai.v34i07.6705"},{"key":"8816_CR42","doi-asserted-by":"crossref","unstructured":"Chen Z, Wang T, Wu X, Hua X-S, Zhang H, Sun Q (2022) Class re-activation maps for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 969\u2013978","DOI":"10.1109\/CVPR52688.2022.00104"},{"key":"8816_CR43","unstructured":"Li J, Jie Z, Wang X, Wei X, Ma L (2022) Expansion and shrinkage of localization for weakly-supervised semantic segmentation. arXiv preprint arXiv:2209.07761"},{"key":"8816_CR44","doi-asserted-by":"crossref","unstructured":"Roy A, Todorovic S (2017) Combining bottom-up, top-down, and smoothness cues for weakly supervised image segmentation. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 3529\u20133538","DOI":"10.1109\/CVPR.2017.770"},{"key":"8816_CR45","doi-asserted-by":"crossref","unstructured":"Chaudhry A, Dokania PK, Torr PH (2017) Discovering class-specific pixels for weakly-supervised semantic segmentation. arXiv preprint arXiv:1707.05821","DOI":"10.5244\/C.31.20"},{"key":"8816_CR46","doi-asserted-by":"crossref","unstructured":"Sun W, Zhang J, Barnes N (2022) Inferring the class conditional response map for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2878\u20132887","DOI":"10.1109\/WACV51458.2022.00271"},{"key":"8816_CR47","doi-asserted-by":"crossref","unstructured":"Li Y, Duan Y, Kuang Z, Chen Y, Zhang W, Li X (2022) Uncertainty estimation via response scaling for pseudo-mask noise mitigation in weakly-supervised semantic segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 1447\u20131455","DOI":"10.1609\/aaai.v36i2.20034"},{"key":"8816_CR48","doi-asserted-by":"crossref","unstructured":"Yu L, Xiang W, Fang J, Chen Y-PP, Chi L (2022) ex-vit: A novel explainable vision transformer for weakly supervised semantic segmentation. arXiv preprint arXiv:2207.05358","DOI":"10.1016\/j.patcog.2023.109666"},{"key":"8816_CR49","unstructured":"Huang J, Wang J, Sun Q, Zhang H (2022) Attention-based class activation diffusion for weakly-supervised semantic segmentation. arXiv preprint arXiv:2211.10931"},{"key":"8816_CR50","unstructured":"Chen J, Zhao X, Luo C, Shen L (2022) Semformer: semantic guided activation transformer for weakly supervised semantic segmentation. arXiv preprint arXiv:2210.14618"},{"issue":"11","key":"8816_CR51","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta R, Shaji A, Smith K, Lucchi A, Fua P, S\u00fcsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274\u20132282","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8816_CR52","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8816_CR53","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbel\u00e1ez P, Bourdev L, Maji S, Malik J (2011) Semantic contours from inverse detectors. In: 2011 international conference on computer vision, pp 991\u2013998 . IEEE","DOI":"10.1109\/ICCV.2011.6126343"},{"issue":"3","key":"8816_CR54","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"issue":"4","key":"8816_CR55","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8816_CR56","doi-asserted-by":"crossref","unstructured":"Lee J, Kim E, Yoon S (2021) Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 4071\u20134080","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"8816_CR57","doi-asserted-by":"crossref","unstructured":"Qin J, Wu J, Xiao X, Li L, Wang X (2022) Activation modulation and recalibration scheme for weakly supervised semantic segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 2117\u20132125","DOI":"10.1609\/aaai.v36i2.20108"},{"key":"8816_CR58","doi-asserted-by":"crossref","unstructured":"Chen T, Yao Y, Zhang L, Wang Q, Xie G, Shen F (2022) Saliency guided inter-and intra-class relation constraints for weakly supervised semantic segmentation. IEEE Trans Multimed","DOI":"10.1109\/TMM.2022.3157481"},{"key":"8816_CR59","doi-asserted-by":"crossref","unstructured":"Chen L, Wu W, Fu C, Han X, Zhang Y (2020) Weakly supervised semantic segmentation with boundary exploration. In: European conference on computer vision, pp 347\u2013362. Springer","DOI":"10.1007\/978-3-030-58574-7_21"},{"key":"8816_CR60","doi-asserted-by":"crossref","unstructured":"Sun K, Shi H, Zhang Z, Huang Y (2021) Ecs-net: improving weakly supervised semantic segmentation by using connections between class activation maps. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7283\u20137292","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"8816_CR61","doi-asserted-by":"crossref","unstructured":"Li K, Wu Z, Peng K-C, Ernst J, Fu Y (2018) Tell me where to look: guided attention inference network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9215\u20139223","DOI":"10.1109\/CVPR.2018.00960"},{"key":"8816_CR62","doi-asserted-by":"crossref","unstructured":"Wang X, You S, Li X, Ma H (2018) Weakly-supervised semantic segmentation by iteratively mining common object features. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 1354\u20131362","DOI":"10.1109\/CVPR.2018.00147"},{"key":"8816_CR63","doi-asserted-by":"crossref","unstructured":"Fan J, Zhang Z, Song C, Tan T (2020) Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4283\u20134292","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"8816_CR64","doi-asserted-by":"publisher","first-page":"14413","DOI":"10.1109\/ACCESS.2020.2966647","volume":"8","author":"Q Yao","year":"2020","unstructured":"Yao Q, Gong X (2020) Saliency guided self-attention network for weakly and semi-supervised semantic segmentation. IEEE Access 8:14413\u201314423","journal-title":"IEEE Access"},{"key":"8816_CR65","first-page":"655","volume":"33","author":"D Zhang","year":"2020","unstructured":"Zhang D, Zhang H, Tang J, Hua X-S, Sun Q (2020) Causal intervention for weakly-supervised semantic segmentation. Adv Neural Inf Process Syst 33:655\u2013666","journal-title":"Adv Neural Inf Process Syst"},{"key":"8816_CR66","doi-asserted-by":"crossref","unstructured":"Kweon H, Yoon S-H, Kim H, Park D, Yoon K-J (2021) Unlocking the potential of ordinary classifier: Class-specific adversarial erasing framework for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6994\u20137003","DOI":"10.1109\/ICCV48922.2021.00691"},{"key":"8816_CR67","doi-asserted-by":"crossref","unstructured":"Lee M, Kim D, Shim H (2022) Threshold matters in wsss: manipulating the activation for the robust and accurate segmentation model against thresholds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4330\u20134339","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"8816_CR68","doi-asserted-by":"crossref","unstructured":"Xu L, Ouyang W, Bennamoun M, Boussaid F, Sohel F, Xu D (2021) Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6984\u20136993","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"8816_CR69","first-page":"27408","volume":"34","author":"J Lee","year":"2021","unstructured":"Lee J, Choi J, Mok J, Yoon S (2021) Reducing information bottleneck for weakly supervised semantic segmentation. Adv Neural Inf Process Syst 34:27408\u201327421","journal-title":"Adv Neural Inf Process Syst"},{"key":"8816_CR70","unstructured":"Zeng Y, Zhuge Y, Lu H, Zhang L (2019) Joint learning of saliency detection and weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7223\u20137233"},{"key":"8816_CR71","unstructured":"Kr\u00e4henb\u00fchl P, Koltun V (2011) Efficient inference in fully connected crfs with gaussian edge potentials. Adv Neural Inf Process Syst. 24"},{"key":"8816_CR72","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.1007\/s11263-020-01293-3","volume":"128","author":"X Wang","year":"2020","unstructured":"Wang X, Liu S, Ma H, Yang M-H (2020) Weakly-supervised semantic segmentation by iterative affinity learning. Int J Comput Vis. 128:1736\u20131749","journal-title":"Int J Comput Vis."},{"key":"8816_CR73","doi-asserted-by":"crossref","unstructured":"Luo W, Yang M (2020) Learning saliency-free model with generic features for weakly-supervised semantic segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 11717\u201311724","DOI":"10.1609\/aaai.v34i07.6842"},{"key":"8816_CR74","doi-asserted-by":"crossref","unstructured":"Su Y, Sun R, Lin G, Wu Q (2021) Context decoupling augmentation for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7004\u20137014","DOI":"10.1109\/ICCV48922.2021.00692"},{"issue":"5","key":"8816_CR75","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s11263-022-01590-z","volume":"130","author":"J Pan","year":"2022","unstructured":"Pan J, Zhu P, Zhang K, Cao B, Wang Y, Zhang D, Han J, Hu Q (2022) Learning self-supervised low-rank network for single-stage weakly and semi-supervised semantic segmentation. Int J Comput Vis 130(5):1181\u20131195","journal-title":"Int J Comput Vis"},{"key":"8816_CR76","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/TIP.2021.3132834","volume":"31","author":"T Zhou","year":"2021","unstructured":"Zhou T, Li L, Li X, Feng C-M, Li J, Shao L (2021) Group-wise learning for weakly supervised semantic segmentation. IEEE Trans Image Process 31:799\u2013811","journal-title":"IEEE Trans Image Process"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08816-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08816-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08816-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T18:12:13Z","timestamp":1697566333000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08816-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":76,"journal-issue":{"issue":"31","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["8816"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08816-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,4]]},"assertion":[{"value":"9 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Code and pre-trained models is available at https:\/\/github.com\/ChunmengLiu1\/MECPformer.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}