An improved recognition and segmentation model for pruning branches of Camellia oleifera trees based on YOLOv8n-seg was proposed, aiming to address the challenges posed by dense interleaving of branches, severe occlus...
详细信息
Wireless sensor networks need simple and effective algorithms to promote the lifetime of these energy limit networks. This article proposed a clustering algorithm: MLUC. We divide the whole network into several layers...
详细信息
Diabetes disease is prevalent worldwide, and predicting its progression is crucial. Several model have been proposed to predict such disease. Those models only determine the disease label, leaving the likelihood of de...
详细信息
Network pruning has a significant role in reducing network parameters and accelerating the inference time of the network. Some existing methods prune the network based on the frequency of the data, and finally obtain ...
详细信息
Network pruning has a significant role in reducing network parameters and accelerating the inference time of the network. Some existing methods prune the network based on the frequency of the data, and finally obtain a sub-network with high accuracy. However, according to our experimental analysis, different frequencies of information in the data contribute differently to the accuracy of the model, and using this information directly for pruning without making a selection will lead to incorrect results. We believe that pruning should retain the convolutional kernels in the network that process important information, while those kernels that process unimportant information should be removed. In this paper, we first investigate the meaning of each frequency band information in the spectrum and their contribution to the prediction accuracy of the network,and according to these results, we propose a new pruning method based on frequency response(PFR). Our PFR finds and removes the convolutional kernels in the network that specialize in processing unimportant information, resulting in a compact neural network model. PFR obtains significant experimental results on different datasets, for example, a 56.0% raduction of float points operations(FLOPs) on Res Net-50 and only 0.37% of Top-1 accuracy degradation on the Image Net dataset.
Background Lip reading uses lip images for visual speech ***-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term tempor...
详细信息
Background Lip reading uses lip images for visual speech ***-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature *** This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency ***,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature *** particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale *** incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more ***,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target *** Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,*** ablation experiments verified the rationality and effectiveness of its *** The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length *** advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.
The rapid spread of fake news significantly impacts social cognition and media credibility, making the effective detection of fake news a critical issue. This paper proposes a fake news detection method based on a com...
详细信息
Graph foundation models and graph prompts have emerged as a popular research area for graph learning research in recent years. However, their real-world deployment raises concerns about the potential leakage of sensit...
详细信息
Graph foundation models and graph prompts have emerged as a popular research area for graph learning research in recent years. However, their real-world deployment raises concerns about the potential leakage of sensitive information during inference. This work presents a new graph encryption for private graph foundation model（GFM） inference with applications for sparse graphs. It adds dummy edges into graphs randomly and encrypts graph structures rather than adjacency matrices through homomorphic encryption（HE）. Based on this kind of graph encryption, we propose a new private GFM inference scheme with graph prompts, and the basic idea is to perform private neighbor queries for the multiplications of adjacency matrices, and integrate neighbor sampling to reduce computation costs. Our scheme achieves a computational complexity of O（M） for HE multiplications, which is a remarkable improvement over the previous O（N2） complexity. Here,N and M are the numbers of nodes and edges in a graph, respectively. Theoretically, we prove the correctness of our private prompted GFM inference and the security of our encryption scheme. Finally, we have conducted extensive experiments to validate the effectiveness and efficiency of our private GFM inference.
The integration of the contrastive learning paradigm into deep clustering has led to enhanced performance in image clustering. However, in existing researches, the samples in the class of the target may be still treat...
详细信息
暂无评论