{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:41:11Z","timestamp":1773330071287,"version":"3.50.1"},"reference-count":31,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2024,1,1]]},"DOI":"10.1587\/transinf.2023edp7079","type":"journal-article","created":{"date-parts":[[2023,12,31]],"date-time":"2023-12-31T22:39:15Z","timestamp":1704062355000},"page":"115-124","source":"Crossref","is-referenced-by-count":2,"title":["Improved Head and Data Augmentation to Reduce Artifacts at Grid Boundaries in Object Detection"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Shinji","family":"UCHINOURA","sequence":"first","affiliation":[{"name":"Hiroshima University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takio","family":"KURITA","sequence":"additional","affiliation":[{"name":"Hiroshima University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.580-587, 2014. 10.1109\/cvpr.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] R. Girshick, \u201cFast r-cnn,\u201d Proc. IEEE international conference on computer vision, pp.1440-1448, 2015. 10.1109\/iccv.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster r-cnn: towards real-time object detection with region proposal networks,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.39, no.6, pp.1137-1149, 2017. 10.1109\/tpami.2016.2577031","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Z. Cai and N. Vasconcelos, \u201cCascade r-cnn: Delving into high quality object detection,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.6154-6162, 2018. 10.1109\/cvpr.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A.C. Berg, \u201cSsd: Single shot multibox detector,\u201d European conference on computer vision, vol.9905, pp.21-37, Springer, 2016. 10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, \u201cYou only look once: Unified, real-time object detection,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.779-788, 2016. 10.1109\/cvpr.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] T.-Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, and S. Belongie, \u201cFeature pyramid networks for object detection,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.2117-2125, 2017. 10.1109\/cvpr.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Doll\u00e1r, \u201cFocal loss for dense object detection,\u201d Proc. IEEE international conference on computer vision, pp.2980-2988, 2017. 10.1109\/iccv.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, \u201cCenternet: Keypoint triplets for object detection,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.6569-6578, 2019. 10.1109\/iccv.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] Z. Tian, C. Shen, H. Chen, and T. He, \u201cFcos: Fully convolutional one-stage object detection,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.9627-9636, 2019. 10.1109\/iccv.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"11","unstructured":"[11] A. Azulay and Y. Weiss, \u201cWhy do deep convolutional networks generalize so poorly to small image transformations?\u201d arXiv preprint arXiv:1805.12177, 2018."},{"key":"12","unstructured":"[12] L. Engstrom, B. Tran, D. Tsipras, L. Schmidt, and A. Madry, \u201cExploring the landscape of spatial robustness,\u201d International conference on machine learning, PMLR, pp.1802-1811, 2019."},{"key":"13","unstructured":"[13] R. Zhang, \u201cMaking convolutional networks shift-invariant again,\u201d International conference on machine learning, PMLR, pp.7324-7334, 2019."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] A. Chaman and I. Dokmani\u0107, \u201cTruly shift-equivariant convolutional neural networks with adaptive polyphase upsampling,\u201d 2021 55th Asilomar Conference on Signals, Systems, and Computers, IEEE, pp.1113-1120, 2021. 10.1109\/ieeeconf53345.2021.9723377","DOI":"10.1109\/IEEECONF53345.2021.9723377"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] M. Manfredi and Y. Wang, \u201cShift equivariance in object detection,\u201d Computer Vision-ECCV 2020 Workshops: Glasgow, UK, Aug. 23-28, 2020, Proceedings, Part VI 16, vol.12540, pp.32-45, Springer, 2020. 10.1007\/978-3-030-65414-6_4","DOI":"10.1007\/978-3-030-65414-6_4"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] A. Chaman and I. Dokmanic, \u201cTruly shift-invariant convolutional neural networks,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.3773-3783, 2021. 10.1109\/cvpr46437.2021.00377","DOI":"10.1109\/CVPR46437.2021.00377"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] X. Zou, F. Xiao, Z. Yu, Y. Li, and Y.J. Lee, \u201cDelving deeper into anti-aliasing in convnets,\u201d International Journal of Computer Vision, vol.131, no.1, pp.67-81, 2023. 10.1007\/s11263-022-01672-y","DOI":"10.1007\/s11263-022-01672-y"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft coco: Common objects in context,\u201d Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, Sept. 6-12, 2014, Proceedings, Part V 13, vol.8693, pp.740-755, Springer, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] M. Tan, R. Pang, and Q.V. Le, \u201cEfficientdet: Scalable and efficient object detection,\u201d Proc. IEEE\/CVF conference on computer vision and pattern recognition, pp.10781-10790, 2020. 10.1109\/cvpr42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"20","unstructured":"[20] A. Bochkovskiy, C.-Y. Wang, and H.-Y.M. Liao, \u201cYolov4: Optimal speed and accuracy of object detection,\u201d arXiv preprint arXiv:2004.10934, 2020."},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] K. He, X. Zhang, S. Ren, and J. Sun, \u201cSpatial pyramid pooling in deep convolutional networks for visual recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.37, no.9, pp.1904-1916, 2015. 10.1109\/tpami.2015.2389824","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"22","unstructured":"[22] Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, \u201cYolox: Exceeding yolo series in 2021,\u201d arXiv preprint arXiv:2107.08430, 2021."},{"key":"23","unstructured":"[23] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., \u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d arXiv preprint arXiv:2010.11929, 2020."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, \u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.10012-10022, 2021. 10.1109\/iccv48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, \u201cGeneralized intersection over union: A metric and a loss for bounding box regression,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.658-666, 2019. 10.1109\/cvpr.2019.00075","DOI":"10.1109\/CVPR.2019.00075"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, \u201cImagenet: A large-scale hierarchical image database,\u201d 2009 IEEE conference on computer vision and pattern recognition, Ieee, pp.248-255, 2009. 10.1109\/cvpr.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDelving deep into rectifiers: Surpassing human-level performance on imagenet classification,\u201d Proc. IEEE international conference on computer vision, pp.1026-1034, 2015. 10.1109\/iccv.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"29","unstructured":"[29] J. Redmon and A. Farhadi, \u201cYolov3: An incremental improvement,\u201d arXiv preprint arXiv:1804.02767, 2018."},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, \u201cPath aggregation network for instance segmentation,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.8759-8768, 2018. 10.1109\/cvpr.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"31","unstructured":"[31] H. Zhang, M. Cisse, Y.N. Dauphin, and D. Lopez-Paz, \u201cmixup: Beyond empirical risk minimization,\u201d arXiv preprint arXiv:1710.09412, 2017."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/1\/E107.D_2023EDP7079\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T04:15:02Z","timestamp":1704514502000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/1\/E107.D_2023EDP7079\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,1]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023edp7079","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,1]]},"article-number":"2023EDP7079"}}