[논문]Mask R-CNN

He, Kaiming; Gkioxari, Georgia; Dollá; r, Piotr; Girshick, Ross

doi:10.1109/tpami.2018.2844175

Mask R-CNN

IEEE transactions on pattern analysis and machine intelligence, v.42 no.2, 2020년, pp.386 - 397

He, Kaiming (Facebook AI Research, Menlo Park, USA) , Gkioxari, Georgia (Facebook AI Research, Menlo Park, USA) , Dollár, Piotr (Facebook AI Research, Menlo Park, USA) , Girshick, Ross

Abstract ▼ AI-Helper

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code has been made available at: https://github.com/facebookresearch/Detectron.

참고문헌 (46)

10.1109/ICCV.2017.97
Ren, Shaoqing, He, Kaiming, Girshick, Ross, Sun, Jian. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE transactions on pattern analysis and machine intelligence, vol.39, no.6, 1137-1149.

상세보기
Beyond skip connections: Top-down modulation for object detection shrivastava 2016
10.1109/CVPR.2017.634
Proc Int Conf Neural Inf Process Spatial transformer networks jaderberg 2015
Proc Int Conf Mach Learn Rectified linear units improve restricted Boltzmann machines nair 2010 807
10.1109/CVPR.2018.00813
Proc Workshop Int Conf Learn Represent Inception-v4, inception-resnet and the impact of residual connections on learning szegedy 2016
10.1109/CVPR.2016.314
10.1109/CVPR.2015.7298641
Hosang, Jan, Benenson, Rodrigo, Dollar, Piotr, Schiele, Bernt. What Makes for Effective Detection Proposals?. IEEE transactions on pattern analysis and machine intelligence, vol.38, no.4, 814-830.

상세보기
10.1109/CVPR.2017.143
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., Jackel, L. D.. Backpropagation Applied to Handwritten Zip Code Recognition. Neural computation, vol.1, no.4, 541-551.

상세보기
Proc Int Conf Neural Inf Process ImageNet classification with deep convolutional neural networks krizhevsky 2012 1097
10.1109/CVPR.2016.89
10.1109/CVPR.2017.106
10.1109/CVPR.2017.351
Proc Eur Conf Comput Vis Simultaneous detection and segmentation hariharan 2014 297
10.1109/CVPR.2015.7298642
10.1109/CVPR.2015.7299025
10.1109/CVPR.2014.49
10.1109/CVPR.2017.100
10.1109/CVPR.2016.90
10.1109/CVPR.2017.305
10.1109/CVPR.2015.7298965
Proc Eur Conf Comput Vis Microsoft COCO: Common objects in context lin 2014 740
10.1109/ICCV.2017.378
Proc Eur Conf Comput Vis Spatial pyramid pooling in deep convolutional networks for visual recognition he 2014 346
10.1109/CVPR.2014.81
10.1109/ICCV.2017.322
Proc Int Conf Neural Inf Process Faster R-CNN: Towards real-time object detection with region proposal networks ren 2015 91
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., Smeulders, A. W. M.. Selective Search for Object Recognition. International journal of computer vision, vol.104, no.2, 154-171.

상세보기
10.1109/ICCV.2015.169
10.1109/CVPR.2016.350
Proc Int Conf Neural Inf Process Learning to segment object candidates pinheiro 2015 1990
10.1109/CVPR.2017.70
Proc Eur Conf Comput Vis Instance-sensitive fully convolutional networks dai 2016 534
Proc Eur Conf Comput Vis Learning to refine object segments pinheiro 2016 75
10.1109/CVPR.2016.511
10.1109/CVPR.2017.472
10.1109/CVPR.2017.395
10.1109/CVPR.2016.343
10.1109/CVPR.2018.00433
10.1109/CVPR.2017.774
10.1109/CVPR.2014.471
Proc Int Conf Neural Inf Process R-FCN: Object detection via region-based fully convolutional networks dai 2016

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Mask R-CNN

Abstract ▼ AI-Helper

참고문헌 (46)

이 논문을 인용한 문헌

관련 콘텐츠

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트