论文标题
关联多尺度的接收场以进行细粒度识别
Associating Multi-Scale Receptive Fields for Fine-grained Recognition
论文作者
论文摘要
提取和融合零件特征已成为罚款颗粒图像识别的关键。最近，非本地（NL）模块在图像识别方面显示出极好的改进。但是，它缺乏建模多尺度部分特征之间相互作用的机制，这对于细粒度识别至关重要。在本文中，我们提出了一个新型的跨层非本地（CNL）模块，以通过两个操作将多尺度的接受场关联。首先，CNL计算查询层的特征与所有响应层之间的相关性。其次，所有响应功能均根据相关性加权，并添加到查询功能中。由于跨层特征的相互作用，我们的模型在多层层之间建立了空间依赖性，并学习了更多的歧视特征。此外，如果我们将低维深层设置为查询层，我们可以降低聚合成本。进行实验以显示我们的模型在三个基准分类基准数据集上实现或超过最先进的结果。我们的代码可以在github.com/fouriye/cnl-icip2020上找到。
Extracting and fusing part features have become the key of fined-grained image recognition. Recently, Non-local (NL) module has shown excellent improvement in image recognition. However, it lacks the mechanism to model the interactions between multi-scale part features, which is vital for fine-grained recognition. In this paper, we propose a novel cross-layer non-local (CNL) module to associate multi-scale receptive fields by two operations. First, CNL computes correlations between features of a query layer and all response layers. Second, all response features are weighted according to the correlations and are added to the query features. Due to the interactions of cross-layer features, our model builds spatial dependencies among multi-level layers and learns more discriminative features. In addition, we can reduce the aggregation cost if we set low-dimensional deep layer as query layer. Experiments are conducted to show our model achieves or surpasses state-of-the-art results on three benchmark datasets of fine-grained classification. Our codes can be found at github.com/FouriYe/CNL-ICIP2020.
