Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance b...
详细信息
Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.
Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech r...
详细信息
Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and softwareengineering. Various deep learning techniques have been successfully employed to facilitate softwareengineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various softwareengineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in softwareengineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for softwareengineering tasks. We still lack surveys explaining the advances of subareas in softwareengineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based softwareengineering. It covers twelve major softwareengineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of softwareengineering, providing one survey covering as many subareas as possible in softwareengineering can help future research push forward the frontier of deep learning-based softwareengineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i
Variational Autoencoders (VAEs) have gained popularity as one of the main approaches for generating diverse and high-quality synthetic images. This study examines the suitability of evaluation metrics, specifically In...
详细信息
This paper situates itself within the broader medical imaging field, focusing on applying generative modelling techniques for anomaly detection in retinal images. Given the complexity of retinal structures, detecting ...
详细信息
The integration of artificial intelligence in agriculture has revolutionized farming practices, enhancing crop yields and resource efficiency. However, existing machine learning systems primarily focus on livestock, o...
详细信息
Most of the research conducted in action recognition is mainly focused on general human action recognition, and most of the available datasets support studies in general human action recognition. In more specific cont...
详细信息
This paper examines the escalating ransomware threats faced by government-managed educational institutions, focusing on their vulnerabilities, case studies, and mitigation strategies. With the adoption of Bring Your O...
详细信息
Multiple patterning lithography (MPL) has been introduced in the integrated circuits manufacturing industry to enhance feature density as the technology node advances. A crucial step of MPL is assigning layout feature...
详细信息
The dynamic knowledge graph is a data structure that adds temporal information to the nodes and edges of a traditional knowledge graph. It describes the changing processes of entities and relationships over time, ther...
详细信息
暂无评论