Roland Hu

Yuxin Zhang, Zuquan Zheng, Roland Hu

Convolutional Neural Network (CNN) is intensively implemented to solve super resolution (SR) tasks because of its superior performance. However, the problem of super resolution is still challenging due to the lack of prior knowledge and small receptive field of CNN. We propose the Segmentation-Piror Self-Attention Generative Adversarial Network (SPSAGAN) to combine segmentation-priors and feature attentions into a unified framework. This combination is led by a carefully designed weighted addition to balance the influence of feature and segmentation attentions, so that the network can emphasize textures in the same segmentation category and meanwhile focus on the long-distance feature relationship. We also propose a lightweight skip connection architecture called Residual-in-Residual Sparse Block (RRSB) to further improve the super-resolution performance and save computation. Extensive experiments show that SPSAGAN can generate more realistic and visually pleasing textures compared to state-of-the-art SFTGAN and ESRGAN on many SR datasets.

Yushu Feng, Huan Wang, Daniel T. Yi et al.

Convolutional neural networks (CNNs) have achieved a great success in face recognition, which unfortunately comes at the cost of massive computation and storage consumption. Many compact face recognition networks are thus proposed to resolve this problem. Triplet loss is effective to further improve the performance of those compact models. However, it normally employs a fixed margin to all the samples, which neglects the informative similarity structures between different identities. In this paper, we propose an enhanced version of triplet loss, named triplet distillation, which exploits the capability of a teacher model to transfer the similarity information to a small model by adaptively varying the margin between positive and negative pairs. Experiments on LFW, AgeDB, and CPLFW datasets show the merits of our method compared to the original triplet loss.

Huan Wang, Qiming Zhang, Yuehai Wang et al.

In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Experiments show that, with 4x speedup, SPP can accelerate AlexNet with only 0.3% loss of top-5 accuracy and VGG-16 with 0.8% loss of top-5 accuracy in ImageNet classification. Moreover, SPP can be directly applied to accelerate multi-branch CNN networks, such as ResNet, without specific adaptations. Our 2x speedup ResNet-50 only suffers 0.8% loss of top-5 accuracy on ImageNet. We further show the effectiveness of SPP on transfer learning tasks.