论文标题
深度张量压缩的来回预测
Back-and-Forth prediction for deep tensor compression
论文作者
论文摘要
与神经网络的协作智能等最新的AI应用程序涉及在各种计算设备之间传输深层功能张量。这需要张量压缩，以优化设备之间的带宽受限通道的使用。在本文中，我们提出了一种用于来源的预测（BAF）预测的预测方案，该预测是为深度特征张量开发的，它使我们能够大大降低张量的大小并提高其可压缩性。我们对最先进的对象检测器进行的实验表明，所提出的方法使我们能够显着减少从模型深处提取的特征张量所需的位数，并且可以忽略的检测性能降解，而无需进行任何网络权重。我们的张量大小减少了62％和75％，同时将网络准确性的损失分别保持在小于1％和2％。
Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices. This necessitates tensor compression in order to optimize the usage of bandwidth-constrained channels between devices. In this paper we present a prediction scheme called Back-and-Forth (BaF) prediction, developed for deep feature tensors, which allows us to dramatically reduce tensor size and improve its compressibility. Our experiments with a state-of-the-art object detector demonstrate that the proposed method allows us to significantly reduce the number of bits needed for compressing feature tensors extracted from deep within the model, with negligible degradation of the detection performance and without requiring any retraining of the network weights. We achieve a 62% and 75% reduction in tensor size while keeping the loss in accuracy of the network to less than 1% and 2%, respectively.
