探索结构化语义先验用于不完整标签下的多标签识别
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels
AI总结：
本文针对不完整标签下的多标签识别，提出利用语义先验提示器构建标签间结构化语义先验，并设计SCPNet及先验增强自监督学习方法，在多个基准数据集上显著超越现有方法。
摘要：
不完整标签下的多标签识别（MLR）极具挑战性。近期工作致力于在视觉-语言模型（即 CLIP）中探索图像到标签的对应关系，以弥补标注不足。尽管性能可观，它们普遍忽视了标签到标签对应关系这一宝贵先验。本文主张通过语义先验提示器（semantic prior prompter）推导标签到标签对应关系的结构化语义先验，以弥补不完整标签下 MLR 的标签监督不足。我们进而提出一种新颖的语义对应提示网络（SCPNet），能够充分探索结构化语义先验。此外，还引入了一种先验增强的自监督学习方法，以加强对该先验的利用。在多个广泛使用的基准数据集上的综合实验与分析表明，我们的方法在所有数据集上显著优于现有方法，充分证明了其有效性和优越性。代码将发布于 https://github.com/jameslahm/SCPNet。
英文摘要：
Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, \ie, CLIP, to compensate for insufficient annotations. In spite of promising performance, they generally overlook the valuable prior about the label-to-label correspondence. In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter. We then present a novel Semantic Correspondence Prompt Network (SCPNet), which can thoroughly explore the structured semantic prior. A Prior-Enhanced Self-Supervised Learning method is further introduced to enhance the use of the prior. Comprehensive experiments and analyses on several widely used benchmark datasets show that our method significantly outperforms existing methods on all datasets, well demonstrating the effectiveness and the superiority of our method. Our code will be available at https://github.com/jameslahm/SCPNet.
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。
