Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing
원문 초록
Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Since the real-world is actually video-based rather than a static state, learning to perform video semantic segmentation is more reasonable and practical for realistic applications. In this paper, we adopt Mask2Former as architecture and ViT-Adapter as backbone. Then, we propose a recyclable semi-supervised training method based on multi-model ensemble. Our method achieves the mIoU scores of 62.97% and 65.83% on Development test and final test respectively. Finally, we obtain the 2nd place in the Video Scene Parsing in the Wild Challenge at CVPR 2023.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment
A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation
VideoMolmo: Spatio-Temporal Grounding Meets Pointing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.