In this paper, the SS wave splitting correction method for multi fracture layers (Yue et al, 2020) was further illustrated for the case of depth-variant fracture orientation and was simplified to an easier-to-implemen...
详细信息
Models trained with adversarial attack can be significantly improved stability and performance when faced with new uncertain environment. In this paper, we propose the robust training framework based on Wasserstein SA...
详细信息
Real-world datasets often exhibit long-tailed distributions, compromising the generalization and fairness of learning-based models. This issue is particularly pronounced in Image Aesthetics Assessment (IAA) tasks, whe...
详细信息
Real-world datasets often exhibit long-tailed distributions, compromising the generalization and fairness of learning-based models. This issue is particularly pronounced in Image Aesthetics Assessment (IAA) tasks, where such imbalance is difficult to mitigate due to a severe distribution mismatch between features and labels, as well as the great sensitivity of aesthetics to image variations. To address these issues, we propose an Enhancer against Long-Tail for Aesthetics-oriented models (ELTA). ELTA first utilizes a dedicated mixup technique to enhance minority feature representation in high-level space while preserving their intrinsic aesthetic qualities. Next, it aligns features and labels through a similarity consistency approach, effectively alleviating the distribution mismatch. Finally, ELTA adopts a specific strategy to refine the output distribution, thereby enhancing the quality of pseudo-labels. Experiments on four representative datasets (AVA, AADB, TAD66K, and PARA) show that our proposed ELTA achieves state-of-the-art performance by effectively mitigating the long-tailed issue in IAA datasets. Moreover, ELTA is designed with plug-and-play capabilities for seamless integration with existing methods. To our knowledge, this is the first contribution in the IAA community addressing long-tail. All resources are available in here. Copyright 2024 by the author(s)
With the continuous enhancement of informatization in production safety, the need to strengthen the analysis capability of big data in production safety is increasingly growing. This is crucial for preventing major ac...
详细信息
Under the rapid development of big data and cloud computing, emerging applications have seen significant improvements in efficiency and service quality. Nevertheless, the conflict between data sharing and privacy pres...
详细信息
With the popularity of cloud storage, data integrity verification has become a challenging issue. Traditional centralized auditing techniques rely on third-party auditors (TPAs), who not only suffer from single points...
详细信息
In video games, procedural content generation has a strong history. Current procedural content generation strategies, such as search-based, solver-based, rule-based, and language-based techniques, have been used to cr...
详细信息
To address the problem of inaccurate prediction of slab quality in continuous casting, an algorithm based on particle swarm optimisation and differential evolution is proposed. The algorithm combines BP neural network...
详细信息
This research presents a novel approach to stream-line the configuration of AUTOSAR (Automotive Open System Architecture) modules using Artificial Intelligence (AI)-based tools. Traditional methods of generating AUTOS...
Safety testing is a key method to ensure software quality. But the quality of the test depends on the level of the test engineers. The method of generating safety test cases based on state diagrams often perform poorl...
详细信息
暂无评论