A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model

29 Dec 2021  ·  Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Han Hu, Xiang Bai ·

Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recognition work well on broader vision problems. This paper targets open-vocabulary semantic segmentation by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images. To remedy the discrepancy in processing granularity, we refuse the use of the prevalent one-stage FCN based framework, and advocate a two-stage semantic segmentation framework, with the first stage extracting generalizable mask proposals and the second stage leveraging an image based CLIP model to perform open-vocabulary classification on the masked image crops which are generated in the first stage. Our experimental results show that this two-stage framework can achieve superior performance than FCN when trained only on COCO Stuff dataset and evaluated on other datasets without fine-tuning. Moreover, this simple framework also surpasses previous state-of-the-arts of zero-shot semantic segmentation by a large margin: +29.5 hIoU on the Pascal VOC 2012 dataset, and +8.9 hIoU on the COCO Stuff dataset. With its simplicity and strong performance, we hope this framework to serve as a baseline to facilitate future research. The code are made publicly available at~\url{https://github.com/MendelXu/zsseg.baseline}.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Open Vocabulary Semantic Segmentation ADE20K-150 SimSeg mIoU 20.5 # 14
Open Vocabulary Semantic Segmentation ADE20K-847 SimSeg mIoU 7 # 13
Open Vocabulary Semantic Segmentation Cityscapes SimSeg mIoU 34.5 # 2
Open Vocabulary Semantic Segmentation COCO-Stuff-171 ZSSeg HIoU 37.8 # 2
Open Vocabulary Semantic Segmentation PASCAL Context-59 SimSeg mIoU 47.7 # 12
Open Vocabulary Semantic Segmentation PascalVOC-20 ZSSeg hIoU 77.5 # 2