{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/single-shot-refinement-neural-network-for","title":"Single-Shot Refinement Neural Network for Object Detection","arxiv_id":"1711.06897","date":"2017-11-18","proceeding":"CVPR 2018 6","authors":["Shifeng Zhang","Longyin Wen","Xiao Bian","Zhen Lei","Stan Z. Li"],"abstract":"For object detection, the two-stage approach (e.g., Faster R-CNN) has been\nachieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has\nthe advantage of high efficiency. To inherit the merits of both while\novercoming their disadvantages, in this paper, we propose a novel single-shot\nbased detector, called RefineDet, that achieves better accuracy than two-stage\nmethods and maintains comparable efficiency of one-stage methods. RefineDet\nconsists of two inter-connected modules, namely, the anchor refinement module\nand the object detection module. Specifically, the former aims to (1) filter\nout negative anchors to reduce search space for the classifier, and (2)\ncoarsely adjust the locations and sizes of anchors to provide better\ninitialization for the subsequent regressor. The latter module takes the\nrefined anchors as the input from the former to further improve the regression\nand predict multi-class label. Meanwhile, we design a transfer connection block\nto transfer the features in the anchor refinement module to predict locations,\nsizes and class labels of objects in the object detection module. The\nmulti-task loss function enables us to train the whole network in an end-to-end\nway. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO\ndemonstrate that RefineDet achieves state-of-the-art detection accuracy with\nhigh efficiency. Code is available at https://github.com/sfzhang15/RefineDet","url_abs":"http://arxiv.org/abs/1711.06897v3","url_pdf":"http://arxiv.org/pdf/1711.06897v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/sfzhang15/RefineDet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/ginn24/RefineDet-1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/jolibrain/caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/kacerj3/caffe-refinedet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/laycoding/FaceDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/laycoding/PostiveDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/laycoding/renlianjiance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/qilei123/RefineDet4OpenImagev4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/RefineDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/MindSpore-scientific-2/code-2/tree/main/SING","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/SING","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/MindSpore-scientific/code-10/tree/main/SING","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/MindSpore-scientific/code-11/tree/main/SING","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/MindSpore-scientific/code-13/tree/main/SING","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/code-implementation1/Code7/tree/main/RefineDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"single-shot-refinement-neural-network-for","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/RefineDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RefineDet512+ (ResNet-101)","rank_in_archive_order":180,"of":225,"metrics":{"AP50":"62.9","AP75":"45.7","APL":"54.1","APM":"45.1","APS":"25.6","box mAP":"41.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RefineDet512+ (VGG-16)","rank_in_archive_order":217,"of":225,"metrics":{"AP50":"58.7","AP75":"40.8","APL":"48.3","APM":"40.3","APS":"22.7","box mAP":"37.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RefineDet512 (ResNet-101)","rank_in_archive_order":223,"of":225,"metrics":{"AP50":"57.5","AP75":"39.5","APL":"51.4","APM":"39.9","APS":"16.6","box mAP":"36.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.06897","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}