Knowledge Consultation for Semi-Supervised Semantic Segmentation

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.

@article{than2025_2503.10693,
  title={ Knowledge Consultation for Semi-Supervised Semantic Segmentation },
  author={ Thuan Than and Nhat-Anh Nguyen-Dang and Dung Nguyen and Salwa K. Al Khatib and Ahmed Elhagry and Hai Phan and Yihui He and Zhiqiang Shen and Marios Savvides and Dang Huynh },
  journal={arXiv preprint arXiv:2503.10693},
  year={ 2025 }
}