对合:反转卷积的固有性以用于视觉识别
Involution: Inverting the Inherence of Convolution for Visual Recognition
摘要:
卷积一直是现代神经网络的核心组成部分,引发了视觉领域深度学习的激增。在这项工作中,我们重新思考了视觉任务的标准卷积的固有原理,特别是空间不可知和通道特定的。相反,我们提出了一种新的原子操作的深度神经网络通过反转上述设计原则的卷积,创造了对合。我们还揭开了最近流行的自我注意力运营商和subsidiaries到我们的对合家庭作为一个过于复杂的实例。所提出的对合运算符可以作为基础砖来构建新一代用于视觉识别的神经网络,为几个流行的基准测试提供不同的深度学习模型,包括ImageNet分类,COCO检测和分割,以及Cityscapes分割。我们基于卷积的模型使用ResNet-50将卷积基线的性能提高了1.6%的top-1准确度,2.5%和2.4%的限界框AP以及4.7%的绝对平均IoU,同时将计算成本分别压缩到上述基准的66%,65%,72%和57%。所有任务的代码和预训练模型都可以在https://github.com/d-li14/involution上找到。
英文摘要:
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard convolution for vision tasks, specifically spatial-agnostic and channel-specific. Instead, we present a novel atomic operation for deep neural networks by inverting the aforementioned design principles of convolution, coined as involution. We additionally demystify the recent popular self-attention operator and subsume it into our involution family as an over-complicated instantiation. The proposed involution operator could be leveraged as fundamental bricks to build the new generation of neural networks for visual recognition, powering different deep learning models on several prevalent benchmarks, including ImageNet classification, COCO detection and segmentation, together with Cityscapes segmentation. Our involution-based models improve the performance of convolutional baselines using ResNet-50 by up to 1.6% top-1 accuracy, 2.5% and 2.4% bounding box AP, and 4.7% mean IoU absolutely while compressing the computational cost to 66%, 65%, 72%, and 57% on the above benchmarks, respectively. Code and pre-trained models for all the tasks are available at https://github.com/d-li14/involution.
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。