通过知识咨询机制提升半监督语义分割性能，不增加模型复杂度
Knowledge Consultation for Semi-Supervised Semantic Segmentation
- 引入双异构主干网络的知识咨询机制，增强伪标签一致性
- 在Pascal VOC上达到89.8% mIoU，优于现有方法
- 适合关注轻量级半监督分割的开发者和研究者
半监督语义分割通过利用未标注数据和先进模型来减少对大量标注数据的依赖，从而提升整体性能。尽管深度协同训练方法已取得成功，但其内在机制仍不明确。本文重新审视基于双异构主干的交叉伪监督方法，提出知识咨询（SegKC）机制以进一步提升分割效果。该方法在Pascal VOC与Cityscapes基准上表现优异，在1/4、1/2和全量划分下分别达到87.1%、89.2%和89.8%的mIoU，同时保持紧凑的模型结构。
原文摘要 · Abstract (English)
Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance. Despite the success of deep co-training methods, their underlying mechanisms remain underexplored. This work revisits Cross Pseudo Supervision with dual heterogeneous backbones and introduces Knowledge Consultation (SegKC) to further enhance segmentation performance. The proposed SegKC achieves significant improvements on Pascal and Cityscapes benchmarks, with mIoU scores of 87.1%, 89.2%, and 89.8% on Pascal VOC with the 1/4, 1/2, and full split partition, respectively, while maintaining a compact model architecture.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。