论文标题
绑定块卷积：更精细，更好的CNN，具有更薄的过滤器
Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
论文作者
论文摘要
卷积是卷积神经网络（CNN）的主要组成部分。我们观察到，随着通道的数量随深度的增加，优化的CNN通常具有高度相关的过滤器，从而降低了特征表示的表达能力。我们提出了绑定的块卷积（TBC），该卷积（TBC）在相等的通道块上共享相同的较薄过滤器，并使用单个滤镜产生多个响应。 TBC的概念也可以扩展到组卷积和完全连接的层，并可以应用于各种骨干网络和注意力模块。我们对分类，检测，实例细分和注意力的广泛实验表明，TBC在标准卷积和群体卷积上的全面增益显着。提出的Tiedse注意模块甚至可以使用比SE模块少的64倍参数来实现可比的性能。特别是，标准CNN通常在遮挡存在下无法准确汇总信息，并导致多种冗余部分对象建议。通过跨通道共享过滤器，TBC可以减少相关性，并有效处理高度重叠的实例。当闭塞比为80％时，TBC将MS-Coco上对象检测的平均精度增加了6％。我们的代码将发布。
Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filters over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates TBC's significant across-the-board gain over standard convolution and group convolution. The proposed TiedSE attention module can even use 64 times fewer parameters than the SE module to achieve comparable performance. In particular, standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals. By sharing filters across channels, TBC reduces correlation and can effectively handle highly overlapping instances. TBC increases the average precision for object detection on MS-COCO by 6% when the occlusion ratio is 80%. Our code will be released.
