We present a novel method of compression of deep Convolutional Neural
Networks (CNNs) by weight sharing through a new representation of convolutional
filters. The proposed method reduces the number of parameters of each
convolutional layer by learning a 1D vector termed Filter Summary (FS). The
convolutional filters are located in FS as overlapping 1D segments, and nearby
filters in FS share weights in their overlapping regions in a natural way. The
resultant neural network based on such weight sharing scheme, termed Filter
Summary CNNs or FSNet, has a FS in each convolution layer instead of a set of
independent filters in the conventional convolution layer. FSNet has the same
architecture as that of the baseline CNN to be compressed, and each convolution
layer of FSNet has the same number of filters from FS as that of the basline
CNN in the forward process. With compelling computational acceleration ratio,
the parameter space of FSNet is much smaller than that of the baseline CNN. In
addition, FSNet is quantization friendly. FSNet with weight quantization leads
to even higher compression ratio without noticeable performance loss. We
further propose Differentiable FSNet where the way filters share weights is
learned in a differentiable and end-to-end manner. Experiments demonstrate the
effectiveness of FSNet in compression of CNNs for computer vision tasks
including image classification and object detection, and the effectiveness of
DFSNet is evidenced by the task of Neural Architecture Search.

提出通过权重共享的卷积核表示的新方法对深度卷积神经网络 (CNNs) 进行压缩，该方法将卷积核定位在 Filter Summary (FS) 中，每个卷积层的参数空间大大减小，且该方法可以轻松适用于权重量化。该文还提出了 Differentiable FSNet，该模型中卷积核之间的权重共享是可区分的。实验结果表明该方法在视觉任务中有效。