Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Scene ParsingScene UnderstandingSemantic SegmentationVideo Semantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning
Semi-Supervised Learning (SSL) with mismatched classes deals with the problem that the classes-of-interests in the limited labeled data is only a subset of the classes in massive unlabeled data. As a result, the classes …
Domain AdaptationZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation
The Associating Objects with Transformers (AOT) framework has exhibited exceptional performance in a wide range of complex scenarios for video object segmentation. In this study, we introduce MSDeAOT, a variant of the AO…
ObjectPositionSegmentationSemantic Segmentation+3C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation
Temporal action segmentation tags action labels for every frame in an input untrimmed video containing multiple actions in a sequence. For the task of temporal action segmentation, we propose an encoder-decoder-style arc…
Action SegmentationDecoderRepresentation LearningSegmentation+1Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024
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. Compared with image scene parsing, vi…
Scene ParsingScene UnderstandingSemantic SegmentationVideo Semantic SegmentationWaste Classification Algorithm
Waste sorting is a major environmental problem. Many have a hard time determining whether waste is organic, meaning food or natural material. Versus recyclable, which are able to be processed and used again. Computer Vis…
Classification