Feature Map Retargeting to Classify Biomedical Journal Figures.
Feature Map Retargeting to Classify Biomedical Journal Figures.
复制标题
DOI：
10.1007/978-3-030-64559-5_58
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Kambhamettu C
中科院分区：
文献类型：
--
作者：
Singh VV;Kambhamettu C
在这项工作中，我们提出了一个层来重定向卷积神经网络（CNN）中的特征映射。我们的“重定位”层在我们提出的空间注意力回归器推断的位置上密集地对每个特征映射通道的值进行采样。我们的层通过将其卷积分量替换为dependency卷积来增加现有的基于显着性的失真层。通过调整其超参数，这种重新表述使Retarget层适用于前馈CNN的任何深度。与内容感知图像大小调整重定向方法保持一致，我们在三个预训练CNN的瓶颈处引入了我们的层。我们在ImageCLEF2013、ImageCLEF2015和ImageCLEF2016文档子图分类任务上验证了我们的方法。我们重新设计的DenseNet121模型与重定向层在视觉类别下实现了最先进的结果，当没有数据增强时。在更深层为特征图的每个通道执行空间采样以指数方式增加了计算成本和存储器需求。为了解决这个问题，我们实验了最近邻插值的近似值，并显示出与基线模型和其他最先进的注意力模型相比的一致改进。该代码可在https://github.com/VimsLab/CNN-Retarget上获得。
In this work, we propose a layer to retarget feature maps in Convolutional Neural Networks (CNNs). Our “Retarget” layer densely samples values for each feature map channel at locations inferred by our proposed spatial attention regressor. Our layer increments an existing saliency-based distortion layer by replacing its convolutional components with depthwise convolutions. This reformulation with the tuning of its hyper-parameters makes the Retarget layer applicable at any depth of feed-forward CNNs. Keeping in spirit with Content-Aware Image Resizing retargeting methods, we introduce our layers at the bottlenecks of three pre-trained CNNs. We validate our approach on the ImageCLEF2013, ImageCLEF2015, and ImageCLEF2016 document subfigure classification task. Our redesigned DenseNet121 model with the Retarget layer achieved state-of-the-art results under the visual category when no data augmentations were performed. Performing spatial sampling for each channel of the feature maps at deeper layers exponentially increases computational cost and memory requirements. To address this, we experiment with an approximation of the nearest neighbor interpolation and show consistent improvement over the baseline models and other state-of-the-art attention models. The code is available at https://github.com/VimsLab/CNN-Retarget.