As convolutional neural networks (CNNs) improve in accuracy, their model size and computational overheads have also increased. These overheads make it challenging to deploy the CNNs on resource-constrained devices. Pruning is a promising technique to mitigate these overheads. In this paper, we propose a novel pruning technique called CURATING that looks at the pruning of CNNs as a multi-objective optimization problem. CURATING retains filters that (i) are very different (less redundant) from each other in terms of their representation (ii) have high saliency score i.e., they reduce the model accuracy drastically if pruned (iii) are likely to produce higher activations. We treat a filter specific to an output channel as a probability distribution over spatial filters to measure the similarity between filters. The similarity matrix is leveraged to create filter embeddings, and we constrain our optimization problem to retain a diverse set of filters based on these filter embeddings. On a range of CNNs over well-known datasets, CURATING exercises a better or comparable tradeoff between model size, accuracy, and inference latency than existing techniques. For example, while pruning VGG16 on the ILSVRC-12 dataset, CURATING achieves higher accuracy and a smaller model size than the previous techniques.

随着卷积神经网络（CNN）准确性的提高，其模型大小和计算开销也随之增加。这些开销给在资源受限的设备上部署CNN带来了挑战。修剪是减轻这些开销的一种很有前途的技术。在本文中，我们提出了一种称为CURATING的新颖修剪技术，该技术将CNN修剪视为多目标优化问题。CURATING保留了（i）就其表示而言彼此非常不同（较少冗余）的过滤器（ii）具有较高的显着性评分，即，如果修剪（iii）可能会产生更高的激活度，则它们会大大降低模型的准确性。我们将特定于输出通道的过滤器视为空间过滤器上的概率分布，以测量过滤器之间的相似性。利用相似度矩阵创建过滤器嵌入，并且我们约束优化问题以基于这些过滤器嵌入保留一组多样化的过滤器。在众所周知的数据集上的一系列CNN上，CURATING在模型大小，准确性和推理延迟之间进行了比现有技术更好或更可比的折衷。例如，在ILSVRC-12数据集上修剪VGG16时，与以前的技术相比，CURATING可实现更高的准确性和更小的模型尺寸。