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.
Recommender systems are techniques designed to enhance user experience in various domains. They suggest relevant items to users based on their behavior and preferences (Linyuan et al. Feb 2012). These systems are bein...
详细信息
The grading of fruits relies on inspections, experiences, and observations, with a proposed system integrating machine learning techniques to assess fruit freshness. By analyzing 2D fruit portrayals based on shape and...
详细信息
Intrusion detection is a prominent factor in the cybersecurity domain that prevents the network from malicious attacks. Cloud security is not satisfactory for securing the user’s information because it is based on st...
详细信息
With advancements in technology, the study of data hiding (DH) in images has become more and more important. In this paper, we introduce a novel data hiding scheme that employs a voting strategy to predict pixels base...
详细信息
Medical imaging has been used extensively in healthcare in recent years for a variety of purposes, including disease diagnosis, treatment planning, and tracking the course of an illness. These applications entail taki...
详细信息
In the modern era, large-scale computing systems distribute tasks into smaller units, allowing them to be executed simultaneously, accelerating job completion, and reducing energy usage. However, cloud computing syste...
详细信息
We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution shifts in the classifier's entropy...
The software development projects’ testing part is usually expensive and complex, but it is essential to gauge the effectiveness of the developed software. Software Fault Prediction (SFP) primarily serves to detect f...
详细信息
The immense volume of data generated and collected by smart devices has significantly enhanced various aspects of our daily lives. However, safeguarding the sensitive information shared among these devices is crucial....
详细信息
暂无评论