지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록· 키워드
오류제보하기
Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a networkadaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.
목차
등록된 정보가 없습니다.
참고문헌 (14)
참고문헌 신청
T. Elsken / 2019 / Neural architecture search : A survey / J. Mach. Learn. Res. 20(1):1~21
B. Zoph / 2017 / Neural architecture search with reinforcement learning / Proc. of Int. Conf. on Learn. Representations :1611.0157~1611.01578
H. Pham / 2018 / Efficient neural architecture search via parameter sharing / Proc. of Int. Conf. on Mach. Learn. :4095~4104
B. Zoph / 2018 / Learning transferable architectures for scalable image recognition / Proc. of IEEE Conf. on Comput. Vis. Pattern Recognit :8697~8710
E. Real / 2019 / Regularized evolution for image classifier architecture search / Proc. of AAAI Conf. on artif. intel. :4780~4789
B. Zoph / 2017 / Neural architecture search with reinforcement learning / Proc. of Int. Conf. on Learn. Representations :1611.0157~1611.01578
H. Pham / 2018 / Efficient neural architecture search via parameter sharing / Proc. of Int. Conf. on Mach. Learn. :4095~4104
B. Zoph / 2018 / Learning transferable architectures for scalable image recognition / Proc. of IEEE Conf. on Comput. Vis. Pattern Recognit :8697~8710
E. Real / 2019 / Regularized evolution for image classifier architecture search / Proc. of AAAI Conf. on artif. intel. :4780~4789
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Training-Free Hardware-Aware Neural Architecture Search with Reinforcement Learning
방송공학회논문지
2021 .12
-
인공 신경망 구조 자동 탐색을 활용한 포도 병해 분류
대한전자공학회 학술대회
2021 .06
-
Memory Efficient Neural Architecture Search for Image Classification
대한전자공학회 학술대회
2021 .06
-
Design of Artificial Neural Network for Human-Centered Risk Assessment of Highly Automated Driving Vehicle
한국자동차공학회 춘계학술대회
2022 .06
-
Modified SaMuNet based on NAS-Bench-201
한국정보과학회 학술발표논문집
2021 .12
-
Self-Attention 연산을 적용한 Neural Architecture Search
한국정보과학회 학술발표논문집
2019 .12
-
GOLDENE ROSE_NOA★ NETWORK OF ARCHITECTURE
월간 데코 DECO
2023 .04
-
깊은 스파이킹 신경망을 위한 뉴럴 아키텍처 탐색 알고리즘 성능 분석
대한전자공학회 학술대회
2023 .06
-
활성 상태의 NAS 시스템 상에서 내부 데이터 수집 기법 연구
정보보호학회논문지
2015 .06
-
이진 까마귀 탐색 알고리즘을 활용한 고추 병해 진단 연구
대한전자공학회 학술대회
2021 .06
-
TSC-NAS: 임베디드 시스템 내 센서 데이터의 On-Device 학습을 위한 신경망 구조 탐색 알고리즘
한국정보과학회 학술발표논문집
2022 .06
-
Finding a High Accuracy Neural Network for the Welding Defects Classification Using Efficient Neural Architecture Search via Parameter Sharing
제어로봇시스템학회 국제학술대회 논문집
2018 .10
-
Experimental study on applying adaptation techniques for deep neural network based voice activity detection
대한전자공학회 학술대회
2017 .01
-
경로 필터링 기반 고효율 NAS 최신 동향
한국통신학회 학술대회논문집
2024 .11
-
Segmentation을 위한 저조도 데이터의 신경망 구조 탐색
Proceedings of KIIT Conference
2022 .12
-
Exploring Knowledge Distribution in Neural Network Parameter
대한전자공학회 학술대회
2019 .06
-
Human-Centered Risk Assessment for Automated Driving Using Deep Learning Through Neural Architecture Search
제어로봇시스템학회 국내학술대회 논문집
2020 .07
-
Performance Comparison of Backbone Networks for Multi-Tasking in Self-Driving Operations
제어로봇시스템학회 국제학술대회 논문집
2022 .11
-
Evaluation of Deep Convolutional Neural Network Architectures for Human Activity Recognition with Smartphone Sensors
한국정보과학회 학술발표논문집
2015 .06
-
Artificial neural network calculations for a receding contact problem
Computers and Concrete, An International Journal
2020 .01
이 논문의 저자 정보
최근 본 자료
댓글(0)
0