{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T03:06:14Z","timestamp":1771297574889,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"China GDSF","award":["2019A1515011949"],"award-info":[{"award-number":["2019A1515011949"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In this paper, we propose a novel target-aware token design for transformer-based object detection. To tackle the target attribute diffusion challenge of transformer-based object detection, we propose two key components in the new target-aware token design mechanism. Firstly, we propose a target-aware sampling module, which forces the sampling patterns to converge inside the target region and obtain its representative encoded features. More specifically, a set of four sampling patterns are designed, including small and large patterns, which focus on the detailed and overall characteristics of a target, respectively, as well as the vertical and horizontal patterns, which handle the object\u2019s directional structures. Secondly, we propose a target-aware key-value matrix. This is a unified, learnable, feature-embedding matrix which is directly weighted on the feature map to reduce the interference of non-target regions. With such a new design, we propose a new variant of the transformer-based object-detection model, called Focal DETR, which achieves superior performance over the state-of-the-art transformer-based object-detection models on the COCO object-detection benchmark dataset. Experimental results demonstrate that our Focal DETR achieves a 44.7 AP in the coco2017 test set, which is 2.7 AP and 0.9 AP higher than the DETR and deformable DETR using the same training strategy and the same feature-extraction network.<\/jats:p>","DOI":"10.3390\/s22228686","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T21:22:02Z","timestamp":1668115322000},"page":"8686","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Focal DETR: Target-Aware Token Design for Transformer-Based Object Detection"],"prefix":"10.3390","volume":"22","author":[{"given":"Tianming","family":"Xie","sequence":"first","affiliation":[{"name":"School of Electronics & Information Engineering, South China University of Technology, Guangzhou 510640, China"},{"name":"National Research Center for Mobile Ultrasonic Detection, Guangzhou 510640, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhonghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronics & Information Engineering, South China University of Technology, Guangzhou 510640, China"},{"name":"National Research Center for Mobile Ultrasonic Detection, Guangzhou 510640, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4084-6911","authenticated-orcid":false,"given":"Jing","family":"Tian","sequence":"additional","affiliation":[{"name":"Institute of Systems Science, National University of Singapore, Singapore 119615, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihong","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electronics & Information Engineering, South China University of Technology, Guangzhou 510640, China"},{"name":"National Research Center for Mobile Ultrasonic Detection, Guangzhou 510640, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_3","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_4","unstructured":"Dai, J., Li, Y., He, K., and Sun, J. (2016, January 5\u201310). R-FCN: Object detection via region-based fully convolutional networks. Proceedings of the Neural Information Processing Systems (NeurIPS), Barcelona, Spain."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_8","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv."},{"key":"ref_9","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_12","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., and Wang, J. (2021, January 11\u201317). Conditional DETR for fast training convergence. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref_15","unstructured":"Wang, Y., Zhang, X., Yang, T., and Sun, J. (2021). Anchor DETR: Query Design for Transformer-Based Object Detection. arXiv."},{"key":"ref_16","unstructured":"Yao, Z., Ai, J., Li, B., and Zhang, C. (2021). Efficient DETR: Improving end-to-end object detector with dense prior. arXiv."},{"key":"ref_17","unstructured":"Lin, J., Mao, X., Chen, Y., Xu, L., He, Y., and Xue, H. (2022). D2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, J., and Tao, D. (2022, January 19\u201320). Recurrent glimpse-based decoder for detection with transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00519"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., and Wang, C. (2021, January 19\u201325). Sparse r-cnn: End-to-end object detection with learnable proposals. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref_20","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., and Shum, H.Y. (2022). Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_22","unstructured":"Parmar, N., Vaswani, A., Uszkoreit, J., Kaiser, L., Shazeer, N., Ku, A., and Tran, D. (2018, January 10\u201315). Image transformer. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_23","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., and Le, Q.V. (November, January 27). Attention augmented convolutional networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., and Doll\u00e1r, P. (2019, January 15\u201320). Panoptic feature pyramid networks. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft COCO: Common objects in context. Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_26","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_27","unstructured":"Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). FCOS: Fully convolutional one-stage object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., and Kitani, K.M. (2021, January 11\u201317). Rethinking transformer-based set prediction for object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., and Chen, J. (2021, January 20\u201325). Up-DETR: Unsupervised pre-training for object detection with transformers. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00165"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8686\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:13:51Z","timestamp":1760145231000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":29,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228686"],"URL":"https:\/\/doi.org\/10.3390\/s22228686","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,10]]}}}