In realistic open-world semi-supervised scenarios, novel classes always emerge from unlabeled data, which leads to the performance degradation of existing semi-supervised learning (SSL) methods. The absence of any sup...
详细信息
In realistic open-world semi-supervised scenarios, novel classes always emerge from unlabeled data, which leads to the performance degradation of existing semi-supervised learning (SSL) methods. The absence of any supervisory signals for novel classes hinders the model from learning disentangled representations, causing the model to confuse known classes with novel classes and generate significant prediction bias towards known classes. In this paper, we propose a hierarchical representation decoupling approach, named OpenHRD, which jointly decouples representations at the instance level and class level for different samples to address this challenge. Specifically, at the instance level, we impose representation constraints on the most similar instance pairs with highest representation similarity to mitigate representation confusion between samples. Furthermore, we also propose an adaptive pseudo-label debiasing regularization method for unlabeled instances at the instance level, which effectively alleviate the prediction bias toward known classes during the model training. At the class level, we introduce an inter-class contrastive learning strategy for novel classes to enlarge the representation distinction between each novel class and other classes. Extensive experimental results on various settings over CIFAR-10, CIFAR-100, and ImageNet-100 demonstrate the superior performance of the proposed OpenHRD. We will release the code at: https://***/srxhlife/OpenHRD.
Nowadays, network slicing (NS) technology has gained widespread adoption within Internet of Things (IoT) systems to meet diverse customized requirements. In the NS based IoT systems, the detection of equipment failure...
详细信息
Mobile edge computation (MEC) is envisioned as a prospective approach for processing the computation-intensive and delay-sensitive tasks of smart mobile devices (SMDs) through offloading them to base stations (BSs) ne...
详细信息
Users employ cloud servers to store data and depend on third-party audits to guarantee data integrity. However, this auditing system poses certain risks, as it may have vulnerabilities that attackers can exploit for i...
详细信息
The Internet of Things (IoT) has revolutionized modern life, yet its interconnected nature poses significant security challenges. This survey investigates threats and countermeasures associated with IoT ecosystems, ca...
详细信息
Hyperspectral images (HSIs) have a wide field of view and rich spectral information, where each pixel represents a small area of the earth's surface. The pixel-level classification task of HSI has become one of th...
详细信息
To protect the vulnerable groups in traffic environment, this paper proposes a V2P protection method with multi-sensor in foggy ***, lidar and camera are combined to achieve mapping 3D point cloud data to the 2D plane...
详细信息
The rapidly developing Deep Learning (DL) techniques have been applied in software systems of various types. However, they can also pose new safety threats with potentially serious consequences, especially in safety-c...
详细信息
The rapidly developing Deep Learning (DL) techniques have been applied in software systems of various types. However, they can also pose new safety threats with potentially serious consequences, especially in safety-critical domains. DL libraries serve as the underlying foundation for DL systems, and bugs in them can have unpredictable impacts that directly affect the behaviors of DL systems. Previous research on fuzzing DL libraries still has limitations in generating tests corresponding to crucial testing scenarios and constructing test oracles. In this paper, we propose MoCo, a novel fuzzing testing method for DL libraries via assembling code. The seed tests used by MoCo are code files that implement DL models, covering both model construction and training in the most common real-world application scenarios for DL libraries. MoCo first disassembles the seed code files to extract templates and code blocks, then applies code block mutation operators (e.g., API replacement, random generation, and boundary checking) to generate new code blocks that fit the template. To ensure the correctness of the code block mutation, we employ the Large Language Model to parse the official documents of DL libraries for information about the parameters and the constraints between them. By inserting context-appropriate code blocks into the template, MoCo can generate a tree of code files with intergenerational relations. According to the derivation relations in this tree, we construct the test oracle based on the execution state consistency and the calculation result consistency. Since the granularity of code assembly is controlled rather than randomly divergent, we can quickly pinpoint the lines of code where the bugs are located and the corresponding triggering conditions. We conduct a comprehensive experiment to evaluate the efficiency and effectiveness of MoCo using three widely-used DL libraries (i.e., TensorFlow, PyTorch, and Jittor). During the experiments, MoCo detects 77 new
In the field of natural language processing, there is no specialized dataset for the Analects, which makes it difficult to assess whether language models can find the semantic relevance between the Analects and modern...
详细信息
In the field of natural language processing, there is no specialized dataset for the Analects, which makes it difficult to assess whether language models can find the semantic relevance between the Analects and modern Mandarin. To address this issue, this paper proposes a dataset named AMPD (Analects-Mandarin parallel Dataset), which includes the Analects and its corresponding modern Mandarin, keywords and their annotations in the Analects, as well as sentiment. Additionally, we propose four baseline tasks and benchmark them by implementing currently popular algorithms respectively. [GRAPHICS]
暂无评论