상세정보
학술대회
DARS: Data Augmentation using Refined Segmentation on Computer Vision Tasks
- 발행일
- 202110
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1-3
- 협약과제
- 21HS1900, 스마트기기를 위한 온디바이스 지능형 정보처리 가속화 SW플랫폼 기술 개발, 김정시
- 초록
- Data augmentation has proven to be effective in improving convolutional neural network performance. As a result, variations of data augmentation methods such as image blending, regional dropout, and copy-paste augmentations has emerged in recent years, enhancing the network's localization and generalization capabilities. However, most data augmentation approach generates unnatural image that contains visible artifacts or strong edges which the network can latch onto. In this paper, we present DARS, a module to refine segmentation in efforts to minimize artifacts for data augmentation. We demonstrated its effectiveness through object classification on Pascal VOC [6] and MS COCO [14] benchmark dataset, with qualitative comparison on refinement from DARS compared to state-of-the-art segmentation models.
- KSP 제안 키워드
- Augmentation approach, Benchmark datasets, Computer Vision(CV), Convolution neural network(CNN), Copy-paste, Data Augmentation, Network performance, Object classification, Qualitative Comparison, image blending, state-of-The-Art