Accelerating Convolutional Neural Networks by Removing Interspatial and Interkernel Redundancies

Filter Pruning via Learned Representation Median in the Frequency Domain

In this article, we propose a novel filter pruning method for deep learning networks by calculating the learned representation median (RM) in frequency domain (LRMF). In contrast to the existing filter pruning methods that remove relatively unimportant filters in the spatial domain, our newly proposed approach emphasizes the removal of absolutely unimportant filters in the frequency domain. Through extensive experiments, we observed that the criterion for "relative unimportance" cannot be generalized well and that the discrete cosine transform (DCT) domain can eliminate redundancy and emphasize low-frequency representation, which is consistent with the human visual system. Based on these important observations, our LRMF calculates the learned RM in the frequency domain and removes its corresponding filter, since it is absolutely unimportant at each layer. Thanks to this, the time-consuming fine-tuning process is not required in LRMF. The results show that LRMF outperforms state-of-the-art pruning methods. For example, with ResNet110 on CIFAR-10, it achieves a 52.3% FLOPs reduction with an improvement of 0.04% in Top-1 accuracy. With VGG16 on CIFAR-100, it reduces FLOPs by 35.9% while increasing accuracy by 0.5%. On ImageNet, ResNet18 and ResNet50 are accelerated by 53.3% and 52.7% with only 1.76% and 0.8% accuracy loss, respectively. The code is based on PyTorch and is available at https://github.com/zhangxin-xd/LRMF.

Soft Person Reidentification Network Pruning via Blockwise Adjacent Filter Decaying

Deep learning has shown significant successes in person reidentification (re-id) tasks. However, most existing works focus on discriminative feature learning and impose complex neural networks, suffering from low inference efficiency. In fact, feature extraction time is also crucial for real-world applications and lightweight models are needed. Prevailing pruning methods usually pay attention to compact classification models. However, these methods are suboptimal for compacting re-id models, which usually produce continuous features and are sensitive to network pruning. The key point of pruning re-id models is how to retain the original filter distribution in continuous features as much as possible. In this work, we propose a blockwise adjacent filter decaying method to fill this gap. Specifically, given a trained model, we first evaluate the redundancy of filters based on the adjacency relationships to preserve the original filter distribution. Second, previous layerwise pruning methods ignore that discriminative information is enhanced block-by-block. Therefore, we propose a blockwise filter pruning strategy to better utilize the block relations in the pretrained model. Third, we propose a novel filter decaying policy to progressively reduce the scale of redundant filters. Different from conventional soft filter pruning that directly sets the filter values as zeros, the proposed filter decaying can keep the pretrained knowledge as much as possible. We evaluate our method on three popular person reidentification datasets, that is: 1) Market-1501; 2) DukeMTMC-reID; and 3) MSMT17_V1. The proposed method shows superior performance to the existing state-of-the-art pruning methods. After pruning over 91.9% parameters on DukeMTMC-reID, the Rank-1 accuracy only drops 3.7%, demonstrating its effectiveness for compacting person reidentification.

Inner-Imaging Networks: Put Lenses Into Convolutional Structure

Despite the tremendous success in computer vision, deep convolutional networks suffer from serious computation costs and redundancies. Although previous works address that by enhancing the diversities of filters, they have not considered the complementarity and the completeness of the internal convolutional structure. To respond to this problem, we propose a novel inner-imaging (InI) architecture, which allows relationships between channels to meet the above requirement. Specifically, we organize the channel signal points in groups using convolutional kernels to model both the intragroup and intergroup relationships simultaneously. A convolutional filter is a powerful tool for modeling spatial relations and organizing grouped signals, so the proposed methods map the channel signals onto a pseudoimage, like putting a lens into the internal convolution structure. Consequently, not only is the diversity of channels increased but also the complementarity and completeness can be explicitly enhanced. The proposed architecture is lightweight and easy to be implement. It provides an efficient self-organization strategy for convolutional networks to improve their performance. Extensive experiments are conducted on multiple benchmark datasets, including CIFAR, SVHN, and ImageNet. Experimental results verify the effectiveness of the InI mechanism with the most popular convolutional networks as the backbones.

Deep neural network correlation learning mechanism for CT brain tumor detection

Modern medical clinics support medical examinations with computer systems which use Computational Intelligence on the way to detect potential health problems in more efficient way. One of the most important applications is evaluation of CT brain scans, where the most precise results come from deep learning approaches. In this article, we propose a novel correlation learning mechanism (CLM) for deep neural network architectures that combines convolutional neural network (CNN) with classic architecture. The support neural network helps CNN to find the most adequate filers for pooling and convolution layers. As a result, the main neural classifier learns faster and reaches higher efficiency. Results show that our CLM model is able to reach about 96% accuracy, and about 95% precision and recall. We have described our proposed mechanism and discussed numerical results to draw conclusions and show future works.

Exploiting deep learning for predictable carbon dot design

In this study, we developed a deep convolution neural network (DCNN) model for predicting the optical properties of carbon dots (CDs), including spectral properties and fluorescence color under ultraviolet irradiation. These results demonstrate the powerful potential of DCNN for guiding the synthesis of CDs.

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks

Deeper and wider convolutional neural networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such overparameterized neural network has received increased attention. A typical pruning algorithm is a three-stage pipeline, i.e., training, pruning, and retraining. Prevailing approaches fix the pruned filters to zero during retraining and, thus, significantly reduce the optimization space. Besides, they directly prune a large number of filters at first, which would cause unrecoverable information loss. To solve these problems, we propose an asymptotic soft filter pruning (ASFP) method to accelerate the inference procedure of the deep neural networks. First, we update the pruned filters during the retraining stage. As a result, the optimization space of the pruned model would not be reduced but be the same as that of the original model. In this way, the model has enough capacity to learn from the training data. Second, we prune the network asymptotically. We prune few filters at first and asymptotically prune more filters during the training procedure. With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable. The experiments show the effectiveness of our ASFP on image classification benchmarks. Notably, on ILSVRC-2012, our ASFP reduces more than 40% FLOPs on ResNet-50 with only 0.14% top-5 accuracy degradation, which is higher than the soft filter pruning by 8%.