Paper ID: 2409.12680

Semi-Supervised Semantic Segmentation with Professional and General Training

Yuting Hong, Hui Xiao, Huazheng Hao, Xiaojie Qiu, Baochen Yao, Chengbin Peng

With the advancement of convolutional neural networks, semantic segmentation has achieved remarkable progress. The training of such networks heavily relies on image annotations, which are very expensive to obtain. Semi-supervised learning can utilize both labeled data and unlabeled data with the help of pseudo-labels. However, in many real-world scenarios where classes are imbalanced, majority classes often play a dominant role during training and the learning quality of minority classes can be undermined. To overcome this limitation, we propose a synergistic training framework, including a professional training module to enhance minority class learning and a general training module to learn more comprehensive semantic information. Based on a pixel selection strategy, they can iteratively learn from each other to reduce error accumulation and coupling. In addition, a dual contrastive learning with anchors is proposed to guarantee more distinct decision boundaries. In experiments, our framework demonstrates superior performance compared to state-of-the-art methods on benchmark datasets.

Submitted: Sep 19, 2024