Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024
This work addresses video scene parsing for computer vision applications, representing an incremental improvement in semi-supervised methods.
The paper tackles semi-supervised video semantic segmentation by using unreliable pseudo labels and a teacher-student network ensemble, achieving mIoU scores of 63.71% and 67.83% on development and final tests, and winning first place in the CVPR 2024 Video Scene Parsing in the Wild Challenge.
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, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction,because the real-world is actually video-based rather than a static state. In this paper, we adopt semi-supervised video semantic segmentation method based on unreliable pseudo labels. Then, We ensemble the teacher network model with the student network model to generate pseudo labels and retrain the student network. Our method achieves the mIoU scores of 63.71% and 67.83% on development test and final test respectively. Finally, we obtain the 1st place in the Video Scene Parsing in the Wild Challenge at CVPR 2024.