arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02891cs.CV
收藏

弱监督语义分割中的多类标记Transformer

Multi-class Token Transformer for Weakly Supervised Semantic Segmentation

The University of Western Australia(西澳大学);The University of Sydney(悉尼大学);Hong Kong University of Science and Technology(香港科技大学)

Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid, Dan Xu

摘要:

本文提出了一种新的基于transformer的框架,学习类特定的对象定位图作为伪标签的弱监督语义分割(WSSS)。受标准视觉Transformer中一类标记的关注区域可以用来形成类不可知的定位图的启发,我们研究了Transformer模型是否也可以通过学习Transformer中的多个类标记来有效地捕获类特定的注意力,以实现更具鉴别力的对象定位。为此,我们提出了一个多类令牌Transformer,称为MCTformer,它使用多个类令牌来学习类令牌和补丁令牌之间的交互。建议的MCTformer可以成功地产生类判别的对象定位地图,从类到补丁的关注对应于不同的类令牌。我们还建议使用一个补丁级成对的亲和力,这是从补丁到补丁Transformer的注意力,以进一步完善本地化地图。此外,所提出的框架,以充分补充类激活映射(CAM)的方法,导致PASCAL VOC和MS COCO数据集上的WSSS结果显着优越。这些结果强调了类标记对于WSSS的重要性。

英文摘要:

This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer model can also effectively capture class-specific attention for more discriminative object localization by learning multiple class tokens within the transformer. To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens. The proposed MCTformer can successfully produce class-discriminative object localization maps from class-to-patch attentions corresponding to different class tokens. We also propose to use a patch-level pairwise affinity, which is extracted from the patch-to-patch transformer attention, to further refine the localization maps. Moreover, the proposed framework is shown to fully complement the Class Activation Mapping (CAM) method, leading to remarkably superior WSSS results on the PASCAL VOC and MS COCO datasets. These results underline the importance of the class token for WSSS.

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。

↑