PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation

In semi-supervised semantic segmentation, the Mean Teacher- and co-training-based approaches are employed to mitigate confirmation bias and coupling problems. However, despite their high performance, these approaches frequently involve complex training pipelines and a substantial computational burden, limiting the scalability and compatibility of these methods. In this paper, we propose a PrevMatch framework that effectively mitigates the aforementioned limitations by maximizing the utilization of the temporal knowledge obtained during the training process. The PrevMatch framework relies on two core strategies: (1) we reconsider the use of temporal knowledge and thus directly utilize previous models obtained…

• MO
  Ministry of Education
• NR
  National Research Foundation

  Award: BK21 FOUR
• NR
  National Research Foundation of Korea