arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09301cs.CV
收藏

基于区分区域的多标记零样本学习

Discriminative Region-based Multi-Label Zero-Shot Learning

Inception Institute of Artificial Intelligence(启智人工智能研究院);Mohamed Bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);Linköping University(林雪平大学);University of Central Florida(中佛罗里达大学)

Sanath Narayan, Akshita Gupta, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Mubarak Shah

摘要:

多标签零样本学习(ZSL)是标准单标签ZSL的更现实的对应部分,因为多个对象可以共存于自然图像中。然而,多个对象的出现使推理复杂化,并且需要对视觉特征进行特定区域的处理以保留其上下文线索。我们注意到,现有的最好的多标签CNOL方法采用了一种共享的方法,通过所有类的一组公共注意力图来关注区域特征。这样的共享地图导致分散的注意力,当类的数量很大时,它不会有区别地集中在相关的位置上。此外,映射空间汇集的视觉特征的类语义导致类间的特征纠缠,从而阻碍了分类。在这里,我们提出了一种替代方法对基于区域的区分度保持多标签zero-shot分类。我们的方法保持了空间分辨率,以保持区域级别的特性,并利用一个双层次的注意力模块(BiAM),以丰富的功能,将区域和场景上下文信息。然后将丰富的区域级特征映射到类语义,并且仅将它们的类预测在空间上合并以获得图像级预测,从而保持多类特征分离。我们的方法在两个大规模多标签zero-shot基准测试:NUS-WIDE和Open Images上设置了一个新的艺术状态。在NUS-WIDE上,我们的方法实现了6.9%mAP的绝对增益,与最好的公布结果相比。

英文摘要:

Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and requires region-specific processing of visual features to preserve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results.

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。

↑