{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:34:00Z","timestamp":1776278040500,"version":"3.50.1"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T00:00:00Z","timestamp":1615420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T00:00:00Z","timestamp":1615420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11263-021-01450-2","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T09:12:30Z","timestamp":1615453950000},"page":"1768-1786","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition"],"prefix":"10.1007","volume":"129","author":[{"given":"Jiebin","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kede","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,11]]},"reference":[{"issue":"5","key":"1450_CR1","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbelaez","year":"2011","unstructured":"Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898\u2013916.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR2","doi-asserted-by":"crossref","unstructured":"Arnab, A., Miksik, O., & Torr\u00a0Philio, H. (2018). On the robustness of semantic segmentation models to adversarial attacks. In IEEE international conference on computer vision and pattern recognition (pp. pp 888\u2013897).","DOI":"10.1109\/CVPR.2018.00099"},{"issue":"12","key":"1450_CR3","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481\u20132495.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR4","unstructured":"Brendel, W., & Bethge, M. (2019). Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet. arXiv preprint arXiv:1904.00760."},{"issue":"1","key":"1450_CR5","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/0146-664X(81)90092-7","volume":"16","author":"PJ Burt","year":"1981","unstructured":"Burt, P. J. (1981). Fast filter transform for image processing. Computer Graphics and Image Processing, 16(1), 20\u201351.","journal-title":"Computer Graphics and Image Processing"},{"issue":"6","key":"1450_CR6","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), 679\u2013698.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR7","doi-asserted-by":"crossref","unstructured":"Cao, L., & Fei-Fei, L. (2007). Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes. In IEEE international conference on computer vision (pp. 1\u20138).","DOI":"10.1109\/ICCV.2007.4408965"},{"issue":"4","key":"1450_CR8","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (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), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR9","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., & Adam, H. (2018a). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587."},{"key":"1450_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018b). Encoder-decoder with atrous separable convolution for semantic image segmentation. In European conference on computer vision (pp. 801\u2013818).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1450_CR11","doi-asserted-by":"crossref","unstructured":"Chen, W., Jiang, Z., Wang, Z., Cui, K., & Qian, X. (2019). Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images. In IEEE International conference on computer vision and pattern recognition (pp. 8924\u20138933).","DOI":"10.1109\/CVPR.2019.00913"},{"key":"1450_CR12","unstructured":"Chen, W., Gong, X., Liu, X., Zhang, Q., Li, Y., & Wang, Z. (2020a). Fasterseg: Searching for faster real-time semantic segmentation. In International conference on learning representations."},{"key":"1450_CR13","unstructured":"Chen, W., Yu, Z., Wang, Z., & Anandkumar, A. (2020b). Automated synthetic-to-real generalization. arXiv preprint arXiv:2007.06965."},{"key":"1450_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, B., Collins, M.D., Zhu, Y., Liu, T., Huang, T.S., Adam, H., & Chen, L.C. (2020). Panoptic-Deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmentation. In IEEE international conference on computer vision and pattern recognition (pp. 12475\u201312485).","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"1450_CR15","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, J.T., & Choo, J. (2020). Cars can\u2019t fly up in the sky: Improving urban-scene segmentation via height-driven attention networks. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 9373\u20139383.","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"1450_CR16","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The Cityscapes dataset for semantic urban scene understanding. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1450_CR17","doi-asserted-by":"crossref","unstructured":"Csurka, G., & Perronnin, F. (2008). A simple high performance approach to semantic segmentation. In: British Machine Vision Conference, pp 1\u201310.","DOI":"10.5244\/C.22.22"},{"key":"1450_CR18","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 886\u2013893.","DOI":"10.1109\/CVPR.2005.177"},{"key":"1450_CR19","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1450_CR20","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Shmelkov, K., Mairal, J., & Schmid, C. (2017). BlitzNet: A real-time deep network for scene understanding. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 4154\u20134162.","DOI":"10.1109\/ICCV.2017.447"},{"issue":"1","key":"1450_CR21","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. M. A., Gool, V. L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"1450_CR22","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2009). Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), 1627\u20131645.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR23","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019a). Dual attention network for scene segmentation. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1450_CR24","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Wang, Y., & Lu, H. (2019b). Stacked deconvolutional network for semantic segmentation. IEEE Transactions on Image Processing (to appear).","DOI":"10.1109\/TIP.2019.2895460"},{"key":"1450_CR25","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., & Brendel, W. (2018). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231."},{"key":"1450_CR26","unstructured":"Golan, T., Raju, P.C., & Kriegeskorte, N. (2019). Controversial stimuli: Pitting neural networks against each other as models of human recognition. arXiv preprint arXiv:1911.09288."},{"key":"1450_CR27","unstructured":"Goodfellow, I.J., Shlens, J., & Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572."},{"key":"1450_CR28","unstructured":"Grenander, U. (2012a). Lectures in Pattern Theory: Pattern Analysis, vol\u00a024. Springer Science & Business Media."},{"key":"1450_CR29","unstructured":"Grenander, U. (2012b). Lectures in Pattern Theory: Pattern Synthesis, vol\u00a018. Springer Science & Business Media."},{"key":"1450_CR30","unstructured":"Grenander, U. (2012c). Lectures in Pattern Theory: Regular Structures, vol\u00a033. Springer Science & Business Media."},{"key":"1450_CR31","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1109\/TIP.2019.2936111","volume":"29","author":"D Guo","year":"2019","unstructured":"Guo, D., Pei, Y., Zheng, K., Yu, H., Lu, Y., & Wang, S. (2019). Degraded image semantic segmentation with dense-gram networks. IEEE Transactions on Image Processing, 29, 782\u2013795.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1450_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1450_CR33","unstructured":"Hendrycks, D., & Dietterich, T. (2019). Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261."},{"key":"1450_CR34","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2019). Natural adversarial examples. arXiv preprint arXiv:1907.07174."},{"key":"1450_CR35","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., & Liu, W. (2019). CCNet: Criss-cross attention for semantic segmentation. In: IEEE International Conference on Computer Vision, pp 603\u2013612.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"1450_CR36","unstructured":"Jacobsen, J.H., Behrmann, J., Zemel, R., & Bethge, M. (2018). Excessive invariance causes adversarial vulnerability. arXiv preprint arXiv:1811.00401."},{"key":"1450_CR37","doi-asserted-by":"crossref","unstructured":"Jia, X., Wang, S., Liang, X., Balagopal, A., Nguyen, D., Yang, M., Wang, Z., Ji, J.X., Qian, X., & Jiang, S. (2019). Cone-beam computed tomography (CBCT) segmentation by adversarial learning domain adaptation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp 567\u2013575.","DOI":"10.1007\/978-3-030-32226-7_63"},{"issue":"2","key":"1450_CR38","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/TIT.1962.1057698","volume":"8","author":"B Julesz","year":"1962","unstructured":"Julesz, B. (1962). Visual pattern discrimination. IRE Transactions on Information Theory, 8(2), 84\u201392.","journal-title":"IRE Transactions on Information Theory"},{"issue":"5802","key":"1450_CR39","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/290091a0","volume":"290","author":"B Julesz","year":"1981","unstructured":"Julesz, B. (1981). Textons, the elements of texture perception, and their interactions. Nature, 290(5802), 91\u201397.","journal-title":"Nature"},{"issue":"2","key":"1450_CR40","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1023\/A:1012460413855","volume":"45","author":"T Kadir","year":"2001","unstructured":"Kadir, T., & Brady, M. (2001). Saliency, scale and image description. International Journal of Computer Vision, 45(2), 83\u2013105.","journal-title":"International Journal of Computer Vision"},{"key":"1450_CR41","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). ImageNet classification with deep convolutional neural networks. In: Nerual Information Processing Systems, pp 1097\u20131105."},{"key":"1450_CR42","unstructured":"Leibe, B., Leonardis, A., & Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. In: Workshop on Statistical Learning in Computer Vision, ECCV, p\u00a07."},{"key":"1450_CR43","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y.Z., & Hospedales, T.M. (2017). Deeper, broader and artier domain generalization. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 5542\u20135550.","DOI":"10.1109\/ICCV.2017.591"},{"key":"1450_CR44","unstructured":"Li, H., Xiong, P., An, J., & Wang, L. (2018). Pyramid attention network for semantic segmentation. arXiv preprint arXiv:1805.10180."},{"key":"1450_CR45","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., & Liu, H. (2019). Expectation-maximization attention networks for semantic segmentation. In: IEEE International Conference on Computer Vision, pp 9167\u20139176.","DOI":"10.1109\/ICCV.2019.00926"},{"key":"1450_CR46","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., & Reid, I. (2017). RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 1925\u20131934.","DOI":"10.1109\/CVPR.2017.549"},{"key":"1450_CR47","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"2","key":"1450_CR48","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"issue":"4","key":"1450_CR49","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/TPAMI.2018.2889948","volume":"42","author":"K Ma","year":"2020","unstructured":"Ma, K., Duanmu, Z., Wang, Z., Wu, Q., Liu, W., Yong, H., et al. (2020). Group maximum differentiation competition: Model comparison with few samples. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(4), 851\u2013864.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"1450_CR50","first-page":"100","volume":"10","author":"WM McKeeman","year":"1998","unstructured":"McKeeman, W. M. (1998). Differential testing for software. Digital Technical Journal, 10(1), 100\u2013107.","journal-title":"Digital Technical Journal"},{"key":"1450_CR51","doi-asserted-by":"crossref","unstructured":"Mehta, S., Hajishirzi, H., & Rastegari, M. (2019a). DiCENet: Dimension-wise convolutions for efficient networks. arXiv preprint arXiv:1906.03516.","DOI":"10.1109\/TPAMI.2020.3041871"},{"key":"1450_CR52","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Shapiro, L., & Hajishirzi, H. (2019b). ESPNetv2: A light-weight, power efficient, and general purpose convolutional neural network. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 9190\u20139200.","DOI":"10.1109\/CVPR.2019.00941"},{"issue":"10","key":"1450_CR53","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","volume":"27","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10), 1615\u20131630.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR54","unstructured":"Miller, G.A. (1998). WordNet: An electronic lexical database. MIT press."},{"key":"1450_CR55","unstructured":"Mohseni, S., Pitale, M., Singh, V., & Wang, Z. (2019). Practical solutions for machine learning safety in autonomous vehicles. arXiv preprint arXiv:1912.09630."},{"key":"1450_CR56","doi-asserted-by":"crossref","unstructured":"Mumford, D. (1994). Pattern theory: A unifying perspective. In: First European Congress of Mathematics, pp 187\u2013224.","DOI":"10.1007\/978-3-0348-9110-3_6"},{"key":"1450_CR57","unstructured":"Nekrasov, V., Shen, C., & Reid, I. (2018). Light-weight refinenet for real-time semantic segmentation. arXiv preprint arXiv:1810.03272."},{"key":"1450_CR58","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Bulo, S.R., & Kontschieder, P. (2017). The Mapillary vistas dataset for semantic understanding of street scenes. In: IEEE International Conference on Computer Vision, pp 4990\u20134999.","DOI":"10.1109\/ICCV.2017.534"},{"key":"1450_CR59","doi-asserted-by":"crossref","unstructured":"Pei, K., Cao, Y., Yang, J., & Jana, S. (2017). DeepXplore: Automated whitebox testing of deep learning systems. In: The 26th Symposium on Operating Systems Principles, pp 1\u201318.","DOI":"10.1145\/3132747.3132785"},{"key":"1450_CR60","doi-asserted-by":"crossref","unstructured":"Peng, C., Zhang, X., Yu, G., Luo, G., & Sun, J. (2017). Large kernel matters\u2013improve semantic segmentation by global convolutional network. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 4353\u20134361.","DOI":"10.1109\/CVPR.2017.189"},{"issue":"1","key":"1450_CR61","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1023\/A:1026553619983","volume":"40","author":"J Portilla","year":"2000","unstructured":"Portilla, J., & Simoncelli, E. P. (2000). A parametric texture model based on joint statistics of complex wavelet coefficients. International Journal of Computer Vision, 40(1), 49\u201370.","journal-title":"International Journal of Computer Vision"},{"key":"1450_CR62","unstructured":"Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do ImageNet classifiers generalize to ImageNet? In: International Conference on Machine Learning, pp 5389\u20135400."},{"key":"1450_CR63","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In: Nerual Information Processing Systems, pp 91\u201399."},{"key":"1450_CR64","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"1450_CR65","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., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1450_CR66","doi-asserted-by":"crossref","unstructured":"Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., & Zisserman, A. (2006). Using multiple segmentations to discover objects and their extent in image collections. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 1605\u20131614.","DOI":"10.1109\/CVPR.2006.326"},{"key":"1450_CR67","unstructured":"Santurkar, S., Tsipras, D., & Madry, A. (2020). BREEDS: Benchmarks for subpopulation shift. arXiv preprint arXiv:2008.04859."},{"issue":"11","key":"1450_CR68","doi-asserted-by":"publisher","first-page":"3440","DOI":"10.1109\/TIP.2006.881959","volume":"15","author":"HR Sheikh","year":"2006","unstructured":"Sheikh, H. R., Sabir, M. F., & Bovik, A. C. (2006). A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Transactions on Image Processing, 15(11), 3440\u20133451.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1450_CR69","doi-asserted-by":"crossref","unstructured":"Shotton, J., Johnson, M., & Cipolla, R. (2008). Semantic texton forests for image categorization and segmentation. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 1\u20138.","DOI":"10.1109\/CVPR.2008.4587503"},{"key":"1450_CR70","doi-asserted-by":"crossref","unstructured":"Simoncelli, E.P., & Freeman, W.T. (1995). The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: IEEE International Conference on Image Processing, pp 444\u2013447.","DOI":"10.1109\/ICIP.1995.537667"},{"key":"1450_CR71","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"1450_CR72","unstructured":"Tsukida, K., & Gupta, M.R. (2011). How to analyze paired comparison data. Technical Report UWEETR-2011-0004, University of Washington, May."},{"key":"1450_CR73","unstructured":"Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014). Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474."},{"key":"1450_CR74","unstructured":"Verbeek, J., & Triggs, B. (2008). Scene segmentation with conditional random fields learned from partially labeled images. In: Nerual Information Processing Systems, pp 1553\u20131560."},{"key":"1450_CR75","first-page":"42","volume":"7","author":"B Wandell","year":"1997","unstructured":"Wandell, B., & Thomas, S. (1997). Foundations of vision. Psyccritiques, 7, 42.","journal-title":"Psyccritiques"},{"key":"1450_CR76","unstructured":"Wang, H., Chen, T., Wang, Z., & Ma, K. (2020). I am going MAD: Maximum discrepancy competition for comparing classifiers adaptively. arXiv preprint arXiv:2002.10648."},{"key":"1450_CR77","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., & Cottrell, G. (2018). Understanding convolution for semantic segmentation. In: IEEE Winter Conference on Applications of Computer Vision, pp 1451\u20131460.","DOI":"10.1109\/WACV.2018.00163"},{"key":"1450_CR78","doi-asserted-by":"publisher","DOI":"10.2200\/S00010ED1V01Y200508IVM003","volume-title":"Modern Image Quality Assessment","author":"Z Wang","year":"2006","unstructured":"Wang, Z., & Bovik, A. C. (2006). Modern Image Quality Assessment. San Rafael, CA, USA: Morgan Claypool publishers."},{"issue":"12","key":"1450_CR79","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1167\/8.12.8","volume":"8","author":"Z Wang","year":"2008","unstructured":"Wang, Z., & Simoncelli, E. P. (2008). Maximum differentiation (MAD) competition: A methodology for comparing computational models of perceptual quantities. Journal of Vision, 8(12), 8\u20138.","journal-title":"Journal of Vision"},{"issue":"4","key":"1450_CR80","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600\u2013612.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1450_CR81","doi-asserted-by":"crossref","unstructured":"Xie, S., & Tu, Z. (2015). Holistically-nested edge detection. In: IEEE International Conference on Computer Vision, pp 1395\u20131403.","DOI":"10.1109\/ICCV.2015.164"},{"key":"1450_CR82","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"issue":"9","key":"1450_CR83","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1109\/TPAMI.2011.208","volume":"34","author":"Y Yang","year":"2012","unstructured":"Yang, Y., Hallman, S., Ramanan, D., & Fowlkes Charless, C. (2012). Layered object models for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1731\u20131743.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1450_CR84","unstructured":"Yu, F., & Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122."},{"key":"1450_CR85","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., & Funkhouser, T. (2017). Dilated residual networks. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 472\u2013480.","DOI":"10.1109\/CVPR.2017.75"},{"key":"1450_CR86","doi-asserted-by":"crossref","unstructured":"Zendel, O., Honauer, K., Murschitz, M., Steininger, D., & Dom\u00ednguez, G.F. (2018). WildDash-Creating hazard-ware benchmarks. In: European Conference on Computer Vision, pp 407\u2013421.","DOI":"10.1007\/978-3-030-01231-1_25"},{"key":"1450_CR87","unstructured":"Zhang, L., Li, X., Arnab, A., Yang, K., Tong, Y., & Torr, P.H. (2019a). Dual graph convolutional network for semantic segmentation. arXiv preprint arXiv:1909.06121."},{"key":"1450_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Yang, Y., Ma, H., & Wu, Y.N. (2019b). Interpreting CNNs via decision trees. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 6261\u20136270.","DOI":"10.1109\/CVPR.2019.00642"},{"key":"1450_CR89","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"1450_CR90","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., & Jia, J. (2018a). ICNet for real-time semantic segmentation on high-resolution images. In: European Conference on Computer Vision, pp 405\u2013420.","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"1450_CR91","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., Shi, J., Change\u00a0Loy, C., Lin, D., & Jia, J. (2018b). PSANet: Point-wise spatial attention network for scene parsing. In: European Conference on Computer Vision, pp 267\u2013283.","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"1450_CR92","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., & Liang, J. (2018). UNet++: A nested U-Net architecture for medical image segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp 3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01450-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01450-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01450-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T18:17:41Z","timestamp":1620238661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01450-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,11]]},"references-count":92,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["1450"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01450-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,11]]},"assertion":[{"value":"30 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2021","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 declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}