With the emergence of pre-trained vision-language models like CLIP, how to adapt them to various downstream classification tasks has garnered significant attention in recent research. The adaptation strategies can be typically categorized into three paradigms: zero-shot adaptation, few-shot adaptation, and the recently-proposed trainingfree few-shot adaptation. Most existing approaches are tailored for a specific setting and can only cater to one or two of these paradigms. In this paper, we introduce a versatile adaptation approach that can effectively work under all three settings. Specifically, we propose the dual memory networks that comprise dynamic and static memory components. The static memory caches training data knowledge, enabling training-free few-shot adaptation, while the dynamic memory preserves historical test features online during the testing process, allowing for the exploration of additional data insights beyond the training set. This novel capability enhances model performance in the fewshot setting and enables model usability in the absence of training data. The two memory networks employ the same flexible memory interactive strategy, which can operate in a training-free mode and can be further enhanced by incorporating learnable projection layers. Our approach is tested across 11 datasets under the three task settings. Remarkably, in the zero-shot scenario, it outperforms existing methods by over 3% and even shows superior results against methods utilizing external training data. Additionally, our method exhibits robust performance against natural distribution shifts. Codes are available at https: //github.com/YBZh/DMN .

With the rapid development of internet communication and the wide application of intelligent terminal, moving the cache to the edge of the network is an effective solution to shorten the delay of users accessing content. However, the existing cache work lacks the comprehensive consideration of users and content, resulting in low cache hit ratio and low accuracy of the whole system. In this paper, the authors propose a collaborative caching model that considers both user request content and content prediction, so as to improve the caching performance of the whole network. Firstly, the model uses the clustering algorithm based on Akike information criterion to cluster users. Then, combined with the clustering results, echo state network is used as the machine learning framework to predict the content. Finally, the cache contents are selected according to the prediction results and cached in the cache unit of the small base station. Simulation results show that compared with the existing cache algorithms, the proposed method has obvious improvement in cache hit ratio, accuracy, and recall rate.

Currently, with the popularity of the internet, people are surrounded by a large number of unhealthy pages which have a serious impact on the physical and mental health of visitors. To protect the legitimate rights and interests of internet users from infringement and maintain the harmonious and stable development of society, a new unhealthy webpage discovery system is needed. First, this paper proposed the knowledge of unhealthy webpages and web crawlers, and then the whole system's plan and design were introduced. The test results show that the unhealthy webpage discovery system can meet the needs of users. This experiment uses a CNN algorithm to classify the text and completes the collection and classification of unhealthy information through URL acquisition and URL filtering. The experimental results show that the unhealthy webpage discovery system based on a convolutional neural network can greatly improve the accuracy of unhealthy webpage discovery and reduce the omission rate, which can meet the needs of users for unhealthy webpage discovery.