Papers › GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
Peng Tu, Yawen Huang, Rongrong Ji, Feng Zheng, Ling Shao
Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the predictions of unlabeled instances consistency alone to regularize networks. However, treating labeled and unlabeled data separately often leads to the discarding of mass prior knowledge learned from the labeled examples, and failure to mine the feature interaction between the labeled and unlabeled image pairs. In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances. Specifically, we first introduce a feature alignment objective between labeled and unlabeled data to capture potentially similar image pairs and then generate mixed inputs from them. The proposed mutual information transfer (MITrans), based on the cluster assumption, is shown to be a powerful knowledge module for further progressive refining features of unlabeled data in the mixed data space. To take advantage of the labeled examples and guide unlabeled data learning, we further propose a mask generation module to generate high-quality pseudo masks for the unlabeled data. Along with supervised learning for labeled data, the prediction of unlabeled data is jointly learned with the generated pseudo masks from the mixed data. Extensive experiments on PASCAL VOC 2012, PASCAL-Context and Cityscapes demonstrate the effectiveness of our GuidedMix-Net, which achieves competitive segmentation accuracy and significantly improves the mIoU by +7% compared to previous state-of-the-art approaches.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Semantic Segmentation | Cityscapes 100 samples labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 56.9% | #9 of 13 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 12.5% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 65.8% | #25 of 33 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 25% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 67.5% | #24 of 30 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 50% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 69.8% | #20 of 23 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL Context 12.5% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 40.3% | #1 of 2 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL Context 25% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 41.7% | #1 of 2 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 1000 labels | GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained) | Validation mIoU | 68.1% | #1 of 1 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 1464 labels | GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained) | Validation mIoU | 73.7 | #16 of 17 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 25% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, input-size: 512x512 with multi-scale and flip, ImageNet pretrained) | Validation mIoU | 77.8% | #15 of 27 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 25% labeled | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 75.5% | #22 of 27 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 50% | GuidedMix-Net(DeepLab v2 with ResNet101, input-size: 512x512 with multi-scale and flip, ImageNet pretrained) | Validation mIoU | 78.2% | #7 of 14 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 50% | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | Validation mIoU | 76.5% | #11 of 14 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 500 labels | GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained) | Validation mIoU | 65.4% | #1 of 1 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Pascal VOC 2012 12.5% labeled | GuidedMix-Net | Validation mIoU | 76.4% | #16 of 38 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Pascal VOC 2012 12.5% labeled | GuidedMix-Net | Validation mIoU | 73.4% | #24 of 38 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections