论文标题
多标签图像识别的语义表示和依赖性学习
Semantic Representation and Dependency Learning for Multi-Label Image Recognition
论文作者
论文摘要
最近，许多多标签图像识别（MLR）作品通过引入预训练的对象检测模型来生成大量建议或利用统计标签共发生，从而增强了不同类别之间的相关性，从而取得了重大进展。但是，这些作品有一些局限性：（1）网络的有效性显着取决于预先训练的对象检测模型，这些模型带来了昂贵且无法承受的计算； （2）当图像中偶尔存在共发生对象时，网络性能会降低，尤其是对于罕见类别。为了解决这些问题，我们提出了一个新颖有效的语义表示和依赖性学习（SRDL）框架，以学习每个类别的特定类别语义表示，并捕获所有类别之间的语义依赖性。具体而言，我们设计了一个特定类别的注意区域（CAR）模块，以生成通道/空间注意矩阵以指导模型以关注语义感知区域。我们还设计了一个对象擦除（OE）模块，以通过擦除语义感知区域以正规化网络培训来隐式地学习类别之间的语义依赖性。在两个流行的MLR基准数据集（即MS-Coco和Pascal VOC 2007）上进行了广泛的实验和比较，证明了该框架对当前最新算法的有效性。
Recently many multi-label image recognition (MLR) works have made significant progress by introducing pre-trained object detection models to generate lots of proposals or utilizing statistical label co-occurrence enhance the correlation among different categories. However, these works have some limitations: (1) the effectiveness of the network significantly depends on pre-trained object detection models that bring expensive and unaffordable computation; (2) the network performance degrades when there exist occasional co-occurrence objects in images, especially for the rare categories. To address these problems, we propose a novel and effective semantic representation and dependency learning (SRDL) framework to learn category-specific semantic representation for each category and capture semantic dependency among all categories. Specifically, we design a category-specific attentional regions (CAR) module to generate channel/spatial-wise attention matrices to guide model to focus on semantic-aware regions. We also design an object erasing (OE) module to implicitly learn semantic dependency among categories by erasing semantic-aware regions to regularize the network training. Extensive experiments and comparisons on two popular MLR benchmark datasets (i.e., MS-COCO and Pascal VOC 2007) demonstrate the effectiveness of the proposed framework over current state-of-the-art algorithms.
