The heavy workload of current deep learning architectures significantly impedes the application of deep learning, especially on resource-constrained devices. Pruning has provided a promising solution to compressing the bloated deep learning models by removing the redundancies of the networks. However, existing pruning methods mainly focus on compressing the superfluous channels without considering layer-level redundancies, which results in the channel-pruned models still suffering from serious redundancies. To mitigate this problem, we propose an effective compression algorithm for deep learning models that uses both the channel-level and layer-level compression techniques to optimize the enormous deep learning models. In detail, the channels are dynamically pruned first, and then the model is further optimized by fusing the redundant layers. Only a minor performance loss results. The experimental results show that the computations of ResNet-110 are reduced by 80.05%, yet the accuracy is only decreased by 0.72%. Forty-eight convolutional layers could be discarded from ResNet-110 with no loss of performance, which fully demonstrates the efficiency of the proposal.

In the promising Artificial Intelligence of Things technology, deep learning algorithms are implemented on edge devices to process data locally. However, high-performance deep learning algorithms are accompanied by increased computation and parameter storage costs, leading to difficulties in implementing huge deep learning algorithms on memory and power constrained edge devices, such as smartphones and drones. Thus various compression methods are proposed, such as channel pruning. According to the analysis of low-level operations on edge devices, existing channel pruning methods have limited effect on latency optimization. Due to data processing operations, the pruned residual blocks still result in significant latency, which hinders real-time processing of CNNs on edge devices. Hence, we propose a generic deep learning architecture optimization method to achieve further acceleration on edge devices. The network is optimized in two stages, Global Constraint and Start-up Latency Reduction, and pruning of both channels and residual blocks is achieved. Optimized networks are evaluated on desktop CPU, FPGA, ARM CPU, and PULP platforms. The experimental results show that the latency is reduced by up to 70.40%, which is 13.63% higher than only applying channel pruning and achieving real-time processing in the edge device.

Deep-learning-based applications bring impressive results to graph machine learning and are widely used in fields such as autonomous driving and language translations. Nevertheless, the tremendous capacity of convolutional neural networks makes it difficult for them to be implemented on resource-constrained devices. Channel pruning provides a promising solution to compress networks by removing a redundant calculation. Existing pruning methods measure the importance of each filter and discard the less important ones until reaching a fixed compression target. However, the static approach limits the pruning effect. Thus, we propose a dynamic channel-pruning method that dynamically identifies and removes less important filters based on a redundancy analysis of its feature maps. Experimental results show that 77.10% of floating-point operations per second (FLOPs) and 91.72% of the parameters are reduced on VGG16BN with only a 0.54% accuracy drop. Furthermore, the compressed models were implemented on the field-programmable gate array (FPGA) and a significant speed-up was observed.

Deploying huge deep learning applications on resource-constrained edge devices is a challenging task. Cloud-based edge computing is a promising solution. Such as model partitioning, a portion of the deep learning model is deployed on the edge device; while, the remaining portion is executed by the cloud. Leveraging the computation power of edge devices, transmission latency is reduced, and bandwidth efficiency is increased. Recently, visual transformer models, supported by large datasets, have dominated in multiple vision tasks. However, model partitioning optimization methods for visual transformers are lacking. Therefore, the paper proposes a cosine similarity-based token subsampling method for visual transformer model partitioning to improve transmission efficiency. Tokens in the same class are subsampled and only the centroid tokens are uploaded. In the cloud, all tokens are reconstructed based on interpolation indexes. Three algorithm implementations are proposed and measured on PC, Jetson NANO and edge CPU Cortex-A53. The experimental results demonstrate that the recommended algorithm implementation can be executed with low-latency of 71.24 ms, and 35.65% transmitted data is reduced with an accuracy drop of 0.46%.

Facial expression recognition has been widely studied and applied in various fields such as healthcare and commerce. However, with the onset of the COVID-19 pandemic, people around the world started wearing masks. Unfortunately, there have been relatively few studies focusing on facial expression recognition under mask-wearing conditions. Therefore, this paper proposes the Masked Facial Expression Classification Network (MFN). Firstly, MFN extracts global features from input images as well as captures local features to mitigate the negative effects of unnecessary information, such as masks, and to emphasize crucial facial regions like the eyes. Secondly, incorporating an attention mechanism into the feature extractor, it allows the model to focus on important regions and channels for facial expression recognition. Lastly, MFN incorporates the metric loss as a discriminative loss because there is a tendency for high similarity in feature distributions among each class for facial expression recognition. This loss aims to minimize the distance between feature vectors of the same class and maximize the distance between feature vectors of different classes. In the experiment using the dataset with individuals wearing masks, the proposed network demonstrated improved accuracy compared to other models.