상세정보
학술지
Benchmarking Deep Learning Models for Instance Segmentation
- 발행일
- 202209
- 출처
- Applied Sciences, v.12 no.17, pp.1-25
- ISSN
- 2076-3417
- 출판사
- MDPI
- 협약과제
- 22HH9200, 실·가상 환경 해석 기반 적응형 인터랙션 기술 개발, 정성욱
- 초록
- Instance segmentation has gained attention in various computer vision fields, such as autonomous driving, drone control, and sports analysis. Recently, many successful models have been developed, which can be classified into two categories: accuracy- and speed-focused. Accuracy and inference time are important for real-time applications of this task. However, these models just present inference time measured on different hardware, which makes their comparison difficult. This study is the first to evaluate and compare the performances of state-of-the-art instance segmentation models by focusing on their inference time in a fixed experimental environment. For precise comparison, the test hardware and environment should be identical; hence, we present the accuracy and speed of the models in a fixed hardware environment for quantitative and qualitative analyses. Although speed-focused models run in real-time on high-end GPUs, there is a trade-off between speed and accuracy when the computing power is insufficient. The experimental results show that a feature pyramid network structure may be considered when designing a real-time model, and a balance between the speed and accuracy must be achieved for real-time application.
- KSP 제안 키워드
- Computer Vision(CV), Computing power, Real-time application, Sports analysis, Trade-off, autonomous driving, deep learning(DL), deep learning models, network structure, real-time model, state-of-The-Art
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
