[논문]Embedded Attention Network for Semantic Segmentation

Lv, Qingxuan; Feng, Mingzhe; Sun, Xin; Dong, Junyu; Chen, Changrui; Zhang, Yu

doi:10.1109/lra.2021.3126892

Embedded Attention Network for Semantic Segmentation

IEEE robotics and automation letters, v.7 no.1, 2022년, pp.326 - 333

Lv, Qingxuan (Ocean University of China, College of Information Science and Engineering, Haide College and Institute of Advanced Ocean Study, Qingdao, Shandong, China) , Feng, Mingzhe (Ocean University of China, College of Information Science and Engineering, Haide College and Institute of Advanced Ocean Study, Qingdao, Shandong, China) , Sun, Xin (Ocean University of China, College of Information Science and Engineering, Haide College and Institute of Advanced Ocean Study, Qingdao, Shandong, China) , Dong, Junyu (Ocean University of China, College of Information Science and Engineering, Haide College and Institute of Advanced Ocean Study, Qingdao, Shandong, China) , Chen, Changrui (Ocean University of China, College of Information Science and Engineering, Haide College and Institute of Advanced Ocean Study, Qingdao, Shandong, China) , Zhang, Yu (Ocean University of China, College of Information Science and Engineering, Haide College and Institu)

Abstract ▼ AI-Helper

Semantic segmentation, as a fundamental task in computer vision, is capable of providing perception ability in many robot applications, such as automatic navigation. To enhance the segmentation accuracy, self-attention mechanism is adopted as a key technique for capturing the long-range dependency and enlarging the receptive fields. However, it requires high computation complexity and GPU memory. In this letter, we propose an Embedded Attention Network to relieve the undesired computational cost. Specifically, we introduce an Embedded Attention (EA) block to improve the segmentation performance and efficiency. Firstly, EA block generates a group of compact while coarse feature bases with the capability of reducing large amount of computation cost. Then an embedded attention is employed to collect the global contextual information and update the representation of the coarse bases from a global view. Finally, the updated bases are leveraged to estimate the attention similarity. We take the well-estimated feature bases to perform feature aggregation. Our approach achieves a considerable computation cost reduction, which suggests it is more powerful than other counterparts in most robot platforms. We conduct extensive experiments on two benchmark semantic segmentation datasets, i.e., CityScapes and ADE20 K. The results demonstrate that the proposed Embedded Attention network delivers comparable performance with high efficiency.

참고문헌 (48)

Giorgini, M., Barbieri, F., Aleotti, J.. Ground Segmentation From Large-Scale Terrestrial Laser Scanner Data of Industrial Environments. IEEE robotics and automation letters, vol.2, no.4, 1948-1955.

상세보기
Hu, Peiyun, Held, David, Ramanan, Deva. Learning to Optimally Segment Point Clouds. IEEE robotics and automation letters, vol.5, no.2, 875-882.

상세보기
Tinchev, Georgi, Penate-Sanchez, Adrian, Fallon, Maurice. Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU. IEEE robotics and automation letters, vol.4, no.2, 1327-1334.

상세보기
Nowicki, Michał R.. Spatiotemporal Calibration of Camera and 3D Laser Scanner. IEEE robotics and automation letters, vol.5, no.4, 6451-6458.

상세보기
Lv, Qingxuan, Sun, Xin, Chen, Changrui, Dong, Junyu, Zhou, Huiyu. Parallel Complement Network for Real-Time Semantic Segmentation of Road Scenes. IEEE transactions on intelligent transportation systems : a publication of the IEEE Intelligent Transportation Systems Council, vol.23, no.5, 4432-4444.

상세보기
Schlemper, Jo, Oktay, Ozan, Schaap, Michiel, Heinrich, Mattias, Kainz, Bernhard, Glocker, Ben, Rueckert, Daniel. Attention gated networks: Learning to leverage salient regions in medical images. Medical image analysis, vol.53, 197-207.

상세보기
Chen, Jingdao, Cho, Yong Kwon, Kira, Zsolt. Multi-View Incremental Segmentation of 3-D Point Clouds for Mobile Robots. IEEE robotics and automation letters, vol.4, no.2, 1240-1246.

상세보기
Kulhánek, Jonáš, Derner, Erik, Babuška, Robert. Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning. IEEE robotics and automation letters, vol.6, no.3, 4345-4352.

상세보기
Krizhevsky, Alex, Sutskever, Ilya, Hinton, Geoffrey E.. ImageNet classification with deep convolutional neural networks. Communications of the ACM, vol.60, no.6, 84-90.

상세보기
10.4324/9781410605337-29
Chen, Changrui, Sun, Xin, Hua, Yang, Dong, Junyu, Xv, Hongwei. Learning Deep Relations to Promote Saliency Detection. Proceedings of the ... aaai conference on artificial intelligence, vol.34, no.7, 10510-10517.

상세보기
Sun, Xin, Xv, Hongwei, Dong, Junyu, Zhou, Huiyu, Chen, Changrui, Li, Qiong. Few-Shot Learning for Domain-Specific Fine-Grained Image Classification. IEEE transactions on industrial electronics : a publication of the IEEE Industrial Electronics Society, vol.68, no.4, 3588-3598.

상세보기
10.1109/CVPR.2015.7298965
Rethinking atrous convolution for semantic image segmentation Chen 2017
Chen, Liang-Chieh, Papandreou, George, Kokkinos, Iasonas, Murphy, Kevin, Yuille, Alan L.. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE transactions on pattern analysis and machine intelligence, vol.40, no.4, 834-848.

상세보기
10.1109/CVPR.2017.660
10.1109/CVPR.2018.00388
10.1109/WACV.2018.00163
Proc. Adv. Neural Inf. Process. Syst. 30 Attention is all you need Vaswani 5998 2017
10.1109/CVPR.2018.00813
Ocnet: Object context network for scene parsing Yuan 2018
10.1109/CVPR.2019.00326
10.1109/ICCV.2019.00069
10.1109/ICCV.2019.00068
10.1109/ICCV.2019.00926
10.1109/ICCV.2019.00690
10.1109/CVPR.2016.350
10.1109/CVPR.2017.544
10.1109/CVPR.2017.549
10.1007/978-3-319-24574-4_28
10.1007/978-3-030-01234-2_49
10.1109/CVPR.2018.00199
High-order paired-aspp networks for semantic segmenation Zhang 2020
Sun, Xin, Chen, Changrui, Wang, Xiaorui, Dong, Junyu, Zhou, Huiyu, Chen, Sheng. Gaussian Dynamic Convolution for Efficient Single-Image Segmentation. IEEE transactions on circuits and systems for video technology : a publication of the Circuits and Systems Society, vol.32, no.5, 2937-2948.

상세보기
10.1109/CVPR.2017.476
Zhang, Yu, Sun, Xin, Dong, Junyu, Chen, Changrui, Lv, Qingxuan. GPNet: Gated pyramid network for semantic segmentation. Pattern recognition, vol.115, 107940-.

상세보기
Dempster, A. P., Laird, N. M., Rubin, D. B.. Maximum Likelihood from Incomplete Data Via the EM Algorithm. Journal of the Royal Statistical Society. Series B (Methodological), vol.39, no.1, 1-22.

상세보기
10.1109/CVPR.2016.90
10.1109/CVPR.2009.5206848
10.1109/CVPR.2018.00591
10.1007/978-3-030-01240-3_17
10.1109/WACV.2018.00163
Wu, Zifeng, Shen, Chunhua, van den Hengel, Anton. Wider or Deeper: Revisiting the ResNet Model for Visual Recognition. Pattern recognition, vol.90, 119-133.

상세보기
10.1007/978-3-030-01261-8_20
10.1007/978-3-030-01228-1_26
10.1109/CVPR.2018.00085
10.1109/ICCV.2017.224
10.1109/CVPR.2018.00747

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

Embedded Attention Network for Semantic Segmentation

Abstract ▼ AI-Helper

참고문헌 (48)

이 논문을 인용한 문헌

관련 콘텐츠

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트