Abstract
This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i.e. various levels of label granularity) to train a powerful human parsing network. In practice, two common application scenarios are addressed, termed universal parsing and dedicated parsing, where the former aims to learn homogeneous human representations from multiple label domains and switch predictions by only using different segmentation heads, and the latter aims to learn a specific domain prediction while distilling the semantic knowledge from other domains. The proposed SST has the following appealing benefits: (1) it can capably serve as an effective training scheme to embed semantic associations of human body parts from multiple label domains into the human representation learning process; (2) it is an extensible semantic transfer framework without predetermining the overall relations of multiple label domains, which allows continuously adding human parsing datasets to promote the training. (3) the relevant modules are only used for auxiliary training and can be removed during inference, eliminating the extra reasoning cost. Experimental results demonstrate SST can effectively achieve promising universal human parsing performance as well as impressive improvements compared to its counterparts on three human parsing benchmarks (i.e., PASCAL-Person-Part, ATR, and CIHP). Code is available at this https URL.
Abstract (translated)
本论文介绍了 Scalable Semantic Transfer (SST),一种新颖的训练范式,旨在探索如何利用来自不同标签域的数据(即不同标签粒度)来训练强大的人类分词网络。在实践中,我们处理了两种常见的应用场景,称为通用分词和专门分词,其中前者旨在从多个标签域中学习统一的人名表示,并仅使用不同的分割头进行预测,而后者旨在学习特定域预测,同时从其他域中萃取语义知识。我们所提出的SST具有以下几个吸引人的优势:(1)它可以轻松地充当有效的训练计划,将来自不同标签域的人名身体部位语义关联嵌入到人名表示学习过程中;(2)它是一个可扩展的语义转移框架,在没有预先决定多个标签域的整体关系的情况下,可以不断添加人类分词数据来促进训练;(3)相关的模块仅用于辅助训练,可以在推理期间删除,消除额外的推理成本。实验结果表明,SST可以有效地实现令人期望的通用人类分词性能,并比其竞品在三个人类分词基准数据上取得了令人印象深刻的进步。代码可在本URL中获取。
URL
https://arxiv.org/abs/2304.04140