Using a Supervised Method without supervision for foreground segmentation
원문 초록
Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on supervision requiring a final training stage on a database of tens to hundreds of manually segmented images from the specific static camera. In this work, we propose a method to automatically create an "artificial" database that is sufficient for training the supervised methods so that it performs better than current unsupervised methods. It is based on combining a weak foreground segmenter, compared to the supervised method, to extract suitable objects from the training images and randomly inserting these objects back into a background image. Test results are shown on the test sequences in CDnet.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning
E-InMeMo: Enhanced Prompting for Visual In-Context Learning
PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation
FOCUS: Towards Universal Foreground Segmentation
A Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data
PartSTAD: 2D-to-3D Part Segmentation Task Adaptation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.