The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 준지도 방식으로 인스턴스 분할을 위한 다양한 훈련 영상을 생성하는 방법을 제안합니다. 제안된 학습 방식에서는 대상 객체의 몇 가지 3D CG 모델과 인터넷에서 키워드로 검색된 다수의 이미지가 각각 초기 모델 훈련 및 모델 업데이트에 사용됩니다. 인스턴스 분할에는 모든 훈련 이미지에 픽셀 수준 주석과 객체 클래스 레이블이 필요합니다. 막대한 주석 비용을 줄이는 가능한 솔루션은 합성 이미지를 교육 이미지로 사용하는 것입니다. 3D CG 시뮬레이터를 이용한 영상 합성은 주석을 자동으로 생성할 수 있지만 시뮬레이터를 위한 다양한 3D 객체 모델을 준비하는 것은 어렵습니다. 또 다른 가능한 해결책은 준지도 학습(semi-supervised learning)입니다. 자가 학습과 같은 준지도 학습은 소규모 지도 데이터 세트와 엄청난 수의 비지도 데이터를 사용합니다. 감독된 이미지는 우리 방법의 3D CG 시뮬레이터에 의해 제공됩니다. 감독되지 않은 이미지에서 올바르게 감지된 주석만 선택해야 합니다. 올바르게 감지된 주석을 선택하기 위해 우리는 실루엣과 질감을 기반으로 감지된 각 주석의 신뢰성을 정량화할 것을 제안합니다. 실험 결과는 제안한 방법이 인스턴스 분할을 개선하기 위해 보다 다양한 이미지를 생성할 수 있음을 보여줍니다.
Takeru OBA
Toyota Technological Institute
Norimichi UKITA
Toyota Technological Institute
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Takeru OBA, Norimichi UKITA, "Instance Segmentation by Semi-Supervised Learning and Image Synthesis" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 6, pp. 1247-1256, June 2020, doi: 10.1587/transinf.2019MVP0016.
Abstract: This paper proposes a method to create various training images for instance segmentation in a semi-supervised manner. In our proposed learning scheme, a few 3D CG models of target objects and a large number of images retrieved by keywords from the Internet are employed for initial model training and model update, respectively. Instance segmentation requires pixel-level annotations as well as object class labels in all training images. A possible solution to reduce a huge annotation cost is to use synthesized images as training images. While image synthesis using a 3D CG simulator can generate the annotations automatically, it is difficult to prepare a variety of 3D object models for the simulator. One more possible solution is semi-supervised learning. Semi-supervised learning such as self-training uses a small set of supervised data and a huge number of unsupervised data. The supervised images are given by the 3D CG simulator in our method. From the unsupervised images, we have to select only correctly-detected annotations. For selecting the correctly-detected annotations, we propose to quantify the reliability of each detected annotation based on its silhouette as well as its textures. Experimental results demonstrate that the proposed method can generate more various images for improving instance segmentation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MVP0016/_p
부
@ARTICLE{e103-d_6_1247,
author={Takeru OBA, Norimichi UKITA, },
journal={IEICE TRANSACTIONS on Information},
title={Instance Segmentation by Semi-Supervised Learning and Image Synthesis},
year={2020},
volume={E103-D},
number={6},
pages={1247-1256},
abstract={This paper proposes a method to create various training images for instance segmentation in a semi-supervised manner. In our proposed learning scheme, a few 3D CG models of target objects and a large number of images retrieved by keywords from the Internet are employed for initial model training and model update, respectively. Instance segmentation requires pixel-level annotations as well as object class labels in all training images. A possible solution to reduce a huge annotation cost is to use synthesized images as training images. While image synthesis using a 3D CG simulator can generate the annotations automatically, it is difficult to prepare a variety of 3D object models for the simulator. One more possible solution is semi-supervised learning. Semi-supervised learning such as self-training uses a small set of supervised data and a huge number of unsupervised data. The supervised images are given by the 3D CG simulator in our method. From the unsupervised images, we have to select only correctly-detected annotations. For selecting the correctly-detected annotations, we propose to quantify the reliability of each detected annotation based on its silhouette as well as its textures. Experimental results demonstrate that the proposed method can generate more various images for improving instance segmentation.},
keywords={},
doi={10.1587/transinf.2019MVP0016},
ISSN={1745-1361},
month={June},}
부
TY - JOUR
TI - Instance Segmentation by Semi-Supervised Learning and Image Synthesis
T2 - IEICE TRANSACTIONS on Information
SP - 1247
EP - 1256
AU - Takeru OBA
AU - Norimichi UKITA
PY - 2020
DO - 10.1587/transinf.2019MVP0016
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2020
AB - This paper proposes a method to create various training images for instance segmentation in a semi-supervised manner. In our proposed learning scheme, a few 3D CG models of target objects and a large number of images retrieved by keywords from the Internet are employed for initial model training and model update, respectively. Instance segmentation requires pixel-level annotations as well as object class labels in all training images. A possible solution to reduce a huge annotation cost is to use synthesized images as training images. While image synthesis using a 3D CG simulator can generate the annotations automatically, it is difficult to prepare a variety of 3D object models for the simulator. One more possible solution is semi-supervised learning. Semi-supervised learning such as self-training uses a small set of supervised data and a huge number of unsupervised data. The supervised images are given by the 3D CG simulator in our method. From the unsupervised images, we have to select only correctly-detected annotations. For selecting the correctly-detected annotations, we propose to quantify the reliability of each detected annotation based on its silhouette as well as its textures. Experimental results demonstrate that the proposed method can generate more various images for improving instance segmentation.
ER -