Pseudo-label Alignment for Semi-supervised Instance Segmentation

Jie Hu, Chen Chen, Liujuan Cao, Shengchuan Zhang, Annan Shu, Guannan Jiang, Rongrong Ji; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 16337-16347


Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable information may be directly filtered out due to mismatches in class and mask quality. To address this issue, we propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper. In PAIS, we devise a dynamic aligning loss (DALoss) that adjusts the weights of semi-supervised loss terms with varying class and mask score pairs. Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited. Notably, with just 1% labeled data, PAIS achieves 21.2 mAP (based on Mask-RCNN) and 19.9 mAP (based on K-Net) on the COCO dataset, outperforming the current state-of-the-art model, i.e., NoisyBoundary with 7.7 mAP, by a margin of over 12 points. Code is available at:

Related Material

[pdf] [arXiv]
@InProceedings{Hu_2023_ICCV, author = {Hu, Jie and Chen, Chen and Cao, Liujuan and Zhang, Shengchuan and Shu, Annan and Jiang, Guannan and Ji, Rongrong}, title = {Pseudo-label Alignment for Semi-supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16337-16347} }