arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.09216cs.CVcs.AI
收藏

SCNet:利用自对比背景原型增强Few-Shot语义分割

SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes

Tsinghua University(清华大学);Tencent Youtu Lab(腾讯优图实验室);University College London(伦敦大学学院)

Jiacheng Chen, Bin-Bin Gao, Zongqing Lu, Jing-Hao Xue, Chengjie Wang, Qingmin Liao

摘要:

Few-Shot语义分割的目标是在查询图像中分割新类别的对象,而支持图像中只有少量带注释的示例。大多数高级解决方案都利用了一个度量学习框架,该框架通过将每个像素与学习到的前景原型相匹配来执行分割。然而,这个框架遭受偏见的分类,由于不完整的建设的样本对前景原型。为了解决这个问题,在本文中,我们引入了一个互补的自我对比任务到Few-Shot语义分割。我们的新模型能够将区域中的像素与该区域的原型相关联,无论它们是在前景还是背景中。为此,我们直接从查询图像中生成自对比背景原型,从而构建完整的样本对,从而完成补充和辅助分割任务,以实现更好的分割模型的训练。在PASCAL-5 $^i$和COCO-20 $^i$上的大量实验清楚地证明了我们的建议的优越性。在不牺牲推理效率的情况下,我们的模型实现了Few-Shot语义分割的1次和5次设置的结果。

英文摘要:

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through matching each pixel to a learned foreground prototype. However, this framework suffers from biased classification due to incomplete construction of sample pairs with the foreground prototype only. To address this issue, in this paper, we introduce a complementary self-contrastive task into few-shot semantic segmentation. Our new model is able to associate the pixels in a region with the prototype of this region, no matter they are in the foreground or background. To this end, we generate self-contrastive background prototypes directly from the query image, with which we enable the construction of complete sample pairs and thus a complementary and auxiliary segmentation task to achieve the training of a better segmentation model. Extensive experiments on PASCAL-5$^i$ and COCO-20$^i$ demonstrate clearly the superiority of our proposal. At no expense of inference efficiency, our model achieves state-of-the results in both 1-shot and 5-shot settings for few-shot semantic segmentation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑