{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T08:55:08Z","timestamp":1793264108746,"version":"4.5.0"},"publisher-location":"Cham","reference-count":108,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728549","type":"print"},{"value":"9783031728556","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72855-6_7","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T18:49:42Z","timestamp":1731091782000},"page":"108-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Sparse Refinement for\u00a0Efficient High-Resolution Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Zhijian","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samir","family":"Khaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenfeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar, M., et al.: A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Inf. Fusion 76, 243\u2013297 (2021)","journal-title":"Inf. Fusion"},{"key":"7_CR2","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.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. TPAMI 39, 2481\u20132495 (2017)","journal-title":"TPAMI"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/978-3-540-24670-1_33","volume-title":"Computer Vision - ECCV 2004","author":"A Blake","year":"2004","unstructured":"Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive image segmentation using an adaptive GMMRF model. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 428\u2013441. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24670-1_33"},{"key":"7_CR4","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: ICLR (2023)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. arXiv (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"7_CR6","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1109\/34.969114","volume":"23","author":"Y Boykov","year":"2001","unstructured":"Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. TPAMI 23, 1222\u20131239 (2001)","journal-title":"TPAMI"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Cai, H., Gan, C., Han, S.: EfficientViT: lightweight multi-scale attention for on-device semantic segmentation. arXiv (2022)","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"7_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-031-25066-8_9","volume-title":"Computer Vision \u2013 ECCV 2022 Workshops","author":"H Cao","year":"2022","unstructured":"Cao, H., et al.: Swin-Unet: Unet-like pure transformer for medical image segmentation. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13803, pp. 205\u2013218. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9"},{"key":"7_CR9","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, K., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)"},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2016","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, K., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI 40, 834\u2013848 (2016)","journal-title":"TPAMI"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: DeepLabv3: encoder-decoder with atrous separable convolution for semantic image segmentation. In: CVPR (2017)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"7_CR12","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. In: CVPR (2017)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: DeepLabv3+: encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"7_CR14","unstructured":"Chen, W., Gong, X., Liu, X., Zhang, Q., Li, Y., Wang, Z.: FasterSeg: searching for faster real-time semantic segmentation. In: ICLR (2020)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., Liu, Z., Tang, H., Yi, L., Zhao, H., Han, S.: SparseViT: revisiting activation sparsity for efficient high-resolution vision transformer. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00205"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00353"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"7_CR18","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal ConvNets: Minkowski convolutional neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"7_CR20","unstructured":"Codella, N.C., et\u00a0al.: Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). In: ISBI (2018)"},{"key":"7_CR21","unstructured":"Contributors, M.: MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Demir, I., et al.: DeepGlobe 2018: a challenge to parse the earth through satellite images. In: CVPR Workshop (2018)","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"7_CR24","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"7_CR25","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: Embracing single stride 3D object detector with sparse transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"7_CR28","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167\u2013181 (2004)","journal-title":"IJCV"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"7_CR30","unstructured":"Gao, P., Ma, T., Li, H., Dai, J., Qiao, Y.: ConvMAE: masked convolution meets masked autoencoders. In: NeurIPS (2022)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Gondimalla, A., Chesnut, N., Thottethodi, M., Vijaykumar, T.: SparTen: a sparse tensor accelerator for convolutional neural networks. In: MICRO (2019)","DOI":"10.1145\/3352460.3358291"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., van\u00a0der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"7_CR33","unstructured":"Guo, M.H., Lu, C.Z., Hou, Q., Liu, Z., Cheng, M.M., Hu, S.M.: SegNeXt: rethinking convolutional attention design for semantic segmentation. In: NeurIPS (2022)"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional neural networks for visual recognition. TPAMI (2015)","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR37","unstructured":"Hong, K., et al.: Exploiting hardware utilization and adaptive dataflow for efficient sparse convolution in 3D point clouds. In: MLSys (2023)"},{"key":"7_CR38","first-page":"3448","volume":"24","author":"Y Hong","year":"2021","unstructured":"Hong, Y., Pan, H., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. T-ITS 24, 3448\u20133460 (2021)","journal-title":"T-ITS"},{"key":"7_CR39","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv (2017)"},{"key":"7_CR40","unstructured":"Huang, L., You, S., Zheng, M., Wang, F., Qian, C., Yamasaki, T.: Green hierarchical vision transformer for masked image modeling. In: NeurIPS (2022)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Huang, Y.H., Proesmans, M., Georgoulis, S., Van\u00a0Gool, L.: Uncertainty based model selection for fast semantic segmentation. In: MVA (2019)","DOI":"10.23919\/MVA.2019.8757930"},{"key":"7_CR42","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$ 0.5MB model size. arXiv (2016)"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"7_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/978-3-031-20083-0_37","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Kong","year":"2022","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via soft token pruning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 620\u2013640. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37"},{"key":"7_CR46","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected crfs with gaussian edge potentials. In: NeurIPS (2011)"},{"key":"7_CR47","unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML (2001)"},{"key":"7_CR48","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on $$\\cal{X}$$-transformed points. In: NeurIPS (2018)"},{"key":"7_CR49","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. In: ICLR (2022)"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhang, Z., Tang, H., Wang, H., Han, S.: PointAcc: efficient point cloud accelerator. In: MICRO (2021)","DOI":"10.1145\/3466752.3480084"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Liu, J., Chen, Y., Ye, X., Tian, Z., Tan, X., Qi, X.: Spatial pruned sparse convolution for efficient 3D object detection. In: NeurIPS (2022)","DOI":"10.1109\/ICIP49359.2023.10222632"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer v2: scaling up capacity and resolution. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR56","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yang, X., Tang, H., Yang, S., Han, S.: FlatFormer: flattened window attention for efficient point cloud transformer. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7_CR58","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)"},{"key":"7_CR59","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"7_CR61","unstructured":"Ma, X., et al.: Image as set of points. In: ICLR (2023)"},{"key":"7_CR62","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., Hajishirzi, H.: ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"7_CR63","unstructured":"NVIDIA: cuBLAS. https:\/\/developer.nvidia.com\/cublas"},{"key":"7_CR64","doi-asserted-by":"crossref","unstructured":"Pan, B., Lin, W., Fang, X., Huang, C., Zhou, B., Lu, C.: Recurrent residual module for fast inference in videos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00166"},{"key":"7_CR65","unstructured":"Pan, B., et al.: VA-RED$$^2$$: video adaptive redundancy reduction. In: ICLR (2021)"},{"key":"7_CR66","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: IA-RED$$^2$$: interpretability-aware redundancy reduction for vision transformers. In: NeurIPS (2021)"},{"key":"7_CR67","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv (2016)"},{"key":"7_CR68","unstructured":"Poudel, R.P., Liwicki, S., Cipolla, R.: Fast-SCNN: fast semantic segmentation network. In: BMVC (2019)"},{"key":"7_CR69","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3d classification and segmentation. In: CVPR (2017)"},{"key":"7_CR70","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"7_CR71","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: NeurIPS (2021)"},{"key":"7_CR72","doi-asserted-by":"crossref","unstructured":"Ren, M., Pokrovsky, A., Urtasun, R.: SBNet: sparse blocks network for fast inference. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00908"},{"key":"7_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"7_CR74","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: \u201cGrabCut\u201d \u2013 interactive foreground extraction using iterated graph cuts. In: SIGGRAPH (2004)","DOI":"10.1145\/1186562.1015720"},{"key":"7_CR75","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"7_CR76","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI 22, 888\u2013905 (2000)","journal-title":"TPAMI"},{"key":"7_CR77","unstructured":"Song, Z., Xu, Y., He, Z., Jiang, L., Jing, N., Liang, X.: CP-ViT: cascade vision transformer pruning via progressive sparsity prediction. arXiv (2022)"},{"key":"7_CR78","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"7_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1007\/978-3-031-20080-9_25","volume-title":"Computer Vision \u2013 ECCV 2022","author":"P Sun","year":"2022","unstructured":"Sun, P., Tan, M., Wang, W., Liu, C., Xia, F., Leng, Z., Anguelov, D.: SWFormer: sparse window transformer for 3D object detection in point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 426\u2013442. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_25"},{"key":"7_CR80","doi-asserted-by":"crossref","unstructured":"Tang, H., Liu, Z., Li, X., Lin, Y., Han, S.: TorchSparse: efficient point cloud inference engine. In: MLSys (2022)","DOI":"10.1109\/CVPRW59228.2023.00025"},{"key":"7_CR81","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/978-3-030-58604-1_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tang","year":"2020","unstructured":"Tang, H., et al.: Searching efficient 3D architectures with sparse point-voxel convolution. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 685\u2013702. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_41"},{"key":"7_CR82","doi-asserted-by":"crossref","unstructured":"Tang, H., et al.: TorchSparse++: efficient training and inference framework for sparse convolution on GPUs. In: MICRO (2023)","DOI":"10.1145\/3613424.3614303"},{"key":"7_CR83","unstructured":"Tian, K., Jiang, Y., Diao, Q., Lin, C., Wang, L., Yuan, Z.: Designing BERT for convolutional networks: sparse and hierarchical masked modeling. In: ICLR (2023)"},{"key":"7_CR84","doi-asserted-by":"publisher","first-page":"2400","DOI":"10.1109\/TPAMI.2022.3162528","volume":"45","author":"T Verelst","year":"2022","unstructured":"Verelst, T., Tuytelaars, T.: SegBlocks: block-based dynamic resolution networks for real-time segmentation. TPAMI 45, 2400\u20132411 (2022)","journal-title":"TPAMI"},{"key":"7_CR85","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: DSVT: dynamic sparse voxel transformer with rotated sets. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"7_CR86","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, Z., Han, S.: SpAtten: effdicient sparse attention architecture with cascade token and head pruning. In: HPCA (2021)","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"7_CR87","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. TPAMI 43, 3349\u20133364 (2020)","journal-title":"TPAMI"},{"key":"7_CR88","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"7_CR89","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, C., Xie, Z., Guo, C., Liu, Y., Leng, J.: Dual-side sparse tensor core. In: ISCA (2021)","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"7_CR90","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. In: SIGGRAPH (2019)","DOI":"10.1145\/3326362"},{"key":"7_CR91","doi-asserted-by":"crossref","unstructured":"Wu, B., Wan, A., Yue, X., Keutzer, K.: SqueezeSeg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"7_CR92","unstructured":"Wu, H., Zhang, J., Huang, K., Liang, K., Yizhou, Y.: FastFCN: rethinking dilated convolution in the backbone for semantic segmentation. arXiv (2019)"},{"key":"7_CR93","doi-asserted-by":"crossref","unstructured":"Wu, T., Lei, Z., Lin, B., Li, C., Qu, Y., Xie, Y.: Patch proposal network for fast semantic segmentation of high-resolution images. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6926"},{"key":"7_CR94","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: NeurIPS (2021)"},{"key":"7_CR95","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors (2018)","DOI":"10.3390\/s18103337"},{"key":"7_CR96","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J., Mallya, A., Kautz, J., Molchanov, P.: AdaViT: adaptive tokens for efficient vision transformer. In: CVPR (2021)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"7_CR97","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: BiSeNet V2: bilateral network with guided aggregation for real-time semantic segmentation. IJCV 129, 3051\u20133068 (2021)","journal-title":"IJCV"},{"key":"7_CR98","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"7_CR99","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"7_CR100","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on ImageNet. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"7_CR101","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-030-58539-6_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 173\u2013190. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_11"},{"key":"7_CR102","unstructured":"Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., Wang, J.: HRFormer: high-resolution transformer for dense prediction. In: NeurIPS (2021)"},{"key":"7_CR103","doi-asserted-by":"crossref","unstructured":"Zhang, G., et al.: RefineMask: towards high-quality instance segmentation with fine-grained features. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00679"},{"key":"7_CR104","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"7_CR105","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, H., Han, S., Dally, W.J.: SpArch: efficient architecture for sparse matrix multiplication. In: HPCA (2020)","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"7_CR106","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"7_CR107","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"7_CR108","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72855-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T19:03:45Z","timestamp":1731092625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72855-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9783031728549","9783031728556"],"references-count":108,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72855-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}