{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T04:12:40Z","timestamp":1748751160146,"version":"3.41.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919787","type":"print"},{"value":"9783031919794","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91979-4_17","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:06:45Z","timestamp":1748718405000},"page":"219-234","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ERF-NAS: Efficient Receptive Field-Based Zero-Shot NAS for\u00a0Object Detection"],"prefix":"10.1007","author":[{"given":"Xinyi","family":"Yu","sequence":"first","affiliation":[]},{"given":"Runan","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Zhihao","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1379-2206","authenticated-orcid":false,"given":"Yongtao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"17_CR1","first-page":"508","volume":"2","author":"H Abdi","year":"2007","unstructured":"Abdi, H.: The Kendall rank correlation coefficient. Encycl. Measure. Stat. 2, 508\u2013510 (2007)","journal-title":"Encycl. Measure. Stat."},{"key":"17_CR2","unstructured":"Bhardwaj, K., et al.: Restructurable activation networks. arXiv preprint arXiv:2208.08562 (2022)"},{"key":"17_CR3","unstructured":"Chen, W., Gong, X., Wang, Z.: Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective. arXiv preprint arXiv:2102.11535 (2021)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: CVPR, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Du, X., et al.: Spinenet: Learning scale-permuted backbone for recognition and localization. In: CVPR, pp. 11592\u201311601 (2020)","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"17_CR6","first-page":"10480","volume":"33","author":"L Dudziak","year":"2020","unstructured":"Dudziak, L., Chau, T., Abdelfattah, M., Lee, R., Kim, H., Lane, N.: Brp-nas: prediction-based nas using gcns. NeurIPS 33, 10480\u201310490 (2020)","journal-title":"NeurIPS"},{"issue":"3","key":"17_CR7","first-page":"1341","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE ITSC 22(3), 1341\u20131360 (2020)","journal-title":"IEEE ITSC"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: CVPR, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"9","key":"17_CR12","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE TPAMI 37(9), 1904\u20131916 (2015)","journal-title":"IEEE TPAMI"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"17_CR15","unstructured":"Jiang, T., Wang, H., Bie, R.: Meco: zero-shot nas with one data and single forward pass via minimum eigenvalue of correlation. NeurIPS 36 (2024)"},{"key":"17_CR16","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLO (Jul 2024). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"17_CR17","unstructured":"Le, H., Borji, A.: What are the receptive, effective receptive, and projective fields of neurons in convolutional neural networks? arXiv preprint arXiv:1705.07049 (2017)"},{"key":"17_CR18","unstructured":"Li, C., et al.: Yolov6 v3. 0: A full-scale reloading. arXiv preprint arXiv:2301.05586 (2023)"},{"key":"17_CR19","unstructured":"Li, G., Yang, Y., Bhardwaj, K., Marculescu, R.: Zico: Zero-shot nas via inverse coefficient of variation on gradients. arXiv preprint arXiv:2301.11300 (2023)"},{"key":"17_CR20","first-page":"6893","volume":"31","author":"T Liang","year":"2022","unstructured":"Liang, T., et al.: CBNet: a composite backbone network architecture for object detection. IEEE TIP 31, 6893\u20136906 (2022)","journal-title":"IEEE TIP"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Lin, M., et al.: Zen-nas: A zero-shot nas for high-performance image recognition. In: ICCV, pp. 347\u2013356 (2021)","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In: ECCV, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: Single shot multibox detector. In: ECCV, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"17_CR25","unstructured":"Long, X., et al.: Pp-yolo: an effective and efficient implementation of object detector. arXiv preprint arXiv:2007.12099 (2020)"},{"key":"17_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103448","volume":"293","author":"W Luo","year":"2021","unstructured":"Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., Kim, T.K.: Multiple object tracking: a literature review. Artif. Intell. 293, 103448 (2021)","journal-title":"Artif. Intell."},{"key":"17_CR27","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. NeurIPS 29 (2016)"},{"key":"17_CR28","unstructured":"Lyu, C., et al.: Rtmdet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)"},{"key":"17_CR29","unstructured":"Mellor, J., Turner, J., Storkey, A., Crowley, E.J.: Neural architecture search without training, pp. 7588\u20137598. PMLR (2021)"},{"key":"17_CR30","unstructured":"NVIDIA: NVIDIA TensorRT (Jul 2024). https:\/\/github.com\/NVIDIA\/TensorRT"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"17_CR33","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. NeurIPS 28 (2015)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Shafiee, M.J., Chywl, B., Li, F., Wong, A.: Fast yolo: a fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943 (2017)","DOI":"10.15353\/vsnl.v3i1.171"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Shen, X., et al.: Deepmad: mathematical architecture design for deep convolutional neural network. In: CVPR, pp. 6163\u20136173 (2023)","DOI":"10.1109\/CVPR52729.2023.00597"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Stamoulis, D., et al.: Single-path nas: Designing hardware-efficient convnets in less than 4 hours. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 481\u2013497. Springer (2019)","DOI":"10.1007\/978-3-030-46147-8_29"},{"key":"17_CR39","unstructured":"Sun, Z., Lin, M., Sun, X., Tan, Z., Li, H., Jin, R.: Mae-det: revisiting maximum entropy principle in zero-shot nas for efficient object detection. arXiv preprint arXiv:2111.13336 (2021)"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: CVPR, pp. 1701\u20131708 (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"17_CR43","first-page":"6377","volume":"33","author":"H Tanaka","year":"2020","unstructured":"Tanaka, H., Kunin, D., Yamins, D.L., Ganguli, S.: Pruning neural networks without any data by iteratively conserving synaptic flow. NeurIPS 33, 6377\u20136389 (2020)","journal-title":"NeurIPS"},{"key":"17_CR44","unstructured":"Wang, C., Zhang, G., Grosse, R.: Picking winning tickets before training by preserving gradient flow. arXiv preprint arXiv:2002.07376 (2020)"},{"key":"17_CR45","unstructured":"Wang, C., et al.: Gold-yolo: efficient object detector via gather-and-distribute mechanism. NeurIPS 36, 51094\u201351112 (2024)"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: CVPR, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Wang, D., Li, M., Gong, C., Chandra, V.: Attentivenas: improving neural architecture search via attentive sampling. In: CVPR, pp. 6418\u20136427 (2021)","DOI":"10.1109\/CVPR46437.2021.00635"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: CVPR, pp. 5265\u20135274 (2018)","DOI":"10.1109\/CVPR.2018.00552"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Wang, N., et al.: Nas-fcos: Fast neural architecture search for object detection. In: CVPR, pp. 11943\u201311951 (2020)","DOI":"10.1109\/CVPR42600.2020.01196"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR, pp. 2411\u20132418 (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-fpn: Automatic network architecture adaptation for object detection beyond classification. In: ICCV, pp. 6649\u20136658 (2019)","DOI":"10.1109\/ICCV.2019.00675"},{"key":"17_CR52","unstructured":"Xu, S.,et\u00a0al.: Pp-yoloe: An evolved version of yolo. arXiv preprint arXiv:2203.16250 (2022)"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Yao, L., Xu, H., Zhang, W., Liang, X., Li, Z.: SM-NAS: Structural-to-modular neural architecture search for object detection. In: AAAI, vol.\u00a034, pp. 12661\u201312668 (2020)","DOI":"10.1609\/aaai.v34i07.6958"},{"issue":"3","key":"17_CR54","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257\u2013276 (2023)","journal-title":"Proc. IEEE"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91979-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:06:55Z","timestamp":1748718415000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91979-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919787","9783031919794"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91979-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}