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 2304.01804cs.CV
收藏

弥合部分标注多标签分类中模型解释的差距

Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification

Seoul National University(首尔国立大学);University of Tübingen(图宾根大学);HodooAI Lab(HodooAI实验室);Inria(法国国家信息与自动化研究所);Ecole normale supérieure(巴黎高等师范学院);CNRS(法国国家科学研究中心);PSL Research University(巴黎文理研究大学);MPI for Intelligent Systems(马克斯·普朗克智能系统研究所)

Youngwook Kim, Jae Myung Kim, Jieun Jeong, Cordelia Schmid, Zeynep Akata, Jungwoo Lee

AI总结:

针对部分标注多标签分类中假阴性标签导致模型归因分数偏低的问题,提出提升部分标签模型归因分数以逼近全标签模型解释的方法,在多个数据集上显著提升分类性能。

摘要:

由于在多标签分类数据集中收集标签的成本高昂,部分标注的多标签分类已成为计算机视觉中的一个新兴领域。该任务的一种基线方法是将未观测到的标签假设为负标签,但这种假设会引入表现为假阴性形式的标签噪声。为了理解假阴性标签造成的负面影响,我们研究了这些标签如何影响模型的解释。我们观察到,分别使用完整标签和部分标签训练的两个模型的解释突出了相似的区域,但具有不同的缩放比例,后者的归因分数往往较低。基于这些发现,我们提出提升使用部分标签训练的模型的归因分数,使其解释类似于使用完整标签训练的模型。即使采用这种概念上简单的方法,在单一正标签设置下的三个不同数据集和大规模部分标签设置下的一个数据集上,多标签分类性能也大幅提升。代码可在 https://github.com/youngwk/BridgeGapExplanationPAMC 获取。

英文摘要:

Due to the expensive costs of collecting labels in multi-label classification datasets, partially annotated multi-label classification has become an emerging field in computer vision. One baseline approach to this task is to assume unobserved labels as negative labels, but this assumption induces label noise as a form of false negative. To understand the negative impact caused by false negative labels, we study how these labels affect the model's explanation. We observe that the explanation of two models, trained with full and partial labels each, highlights similar regions but with different scaling, where the latter tends to have lower attribution scores. Based on these findings, we propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels. Even with the conceptually simple approach, the multi-label classification performance improves by a large margin in three different datasets on a single positive label setting and one on a large-scale partial label setting. Code is available at https://github.com/youngwk/BridgeGapExplanationPAMC.

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。

↑