Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
This work addresses the problem of reducing annotation costs for semantic segmentation in computer vision, presenting an incremental improvement over existing methods.
The paper tackles semi-supervised semantic segmentation by jointly enforcing label-space consistency and feature-space contrastive properties, achieving state-of-the-art performance with the PC2Seg method on VOC, Cityscapes, and COCO datasets.
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.