Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

About

In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good segmentation boundaries, they are prone to confuse classes with similar visual appearance due to the limited supervision. On the other hand, vision-language models (VLMs) are able to learn diverse semantic knowledge from image-caption datasets but produce noisy segmentation due to the image-level training. In SemiVL, we propose to integrate rich priors from VLM pre-training into semi-supervised semantic segmentation to learn better semantic decision boundaries. To adapt the VLM from global to local reasoning, we introduce a spatial fine-tuning strategy for label-efficient learning. Further, we design a language-guided decoder to jointly reason over vision and language. Finally, we propose to handle inherent ambiguities in class labels by providing the model with language guidance in the form of class definitions. We evaluate SemiVL on 4 semantic segmentation datasets, where it significantly outperforms previous semi-supervised methods. For instance, SemiVL improves the state-of-the-art by +13.5 mIoU on COCO with 232 annotated images and by +6.1 mIoU on Pascal VOC with 92 labels. Project page: https://github.com/google-research/semivl

Lukas Hoyer, David Joseph Tan, Muhammad Ferjad Naeem, Luc Van Gool, Federico Tombari• 2023

Related benchmarks

TaskDatasetResultRank
Change DetectionLEVIR-CD (test)--
357
Semantic segmentationPascal VOC (Original set)
mIoU87.3
105
Semantic segmentationCityscapes 1/4 (744 labels)
mIoU80.3
80
Semantic segmentationCityscapes 1/16 (186 labeled samples)
mIoU77.9
68
Semantic segmentationCITYSCAPES 1/8 labeled samples 372 labels (val)
mIoU79.4
65
Semantic segmentationPascal VOC 1/16 labeled 2012 (train)
mIoU84
53
Semantic segmentationPascal VOC Original protocol 92 labeled images
mIoU84
48
Semantic segmentationPascal VOC Original protocol 1464 labeled images
mIoU87.3
36
Semantic segmentationPascal VOC 183 labeled images (Original protocol)
mIoU85.6
34
Semantic segmentationPascal VOC 366 labeled images (Original protocol)
mIoU86
34
Showing 10 of 38 rows

Other info

Code

Follow for update