Continuous performance monitoring is critical for maintaining optimal performance of High-Performance Computing resources. This is especially important for technological test bed systems, in which software updates occ...
详细信息
Rainfall is the main cause of flood disasters, and analyzing its features plays a crucial role in preventing flood disasters. How to extract rainfall process features and conduct rainfall similarity analysis is a chal...
详细信息
With the rising popularity of online social interactions, emojis play a pivotal role in communication, effectively conveying people's emotions. Hence, accurately converting facial micro-expressions into correspond...
详细信息
Space systems enable essential communications, navigation, imaging and sensing for a variety of domains, including agriculture, commerce, transportation, and emergency operations by first responders. Protecting the cy...
详细信息
We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using_only local computations and communications. Previous...
详细信息
In 3D human pose estimation, binocular vision typically relies on stereo matching to obtain depth information and calculates 3D keypoints using the disparity principle. However, the high computational cost of stereo m...
详细信息
Due to the aging of the world's population, the incidence of retinal diseases is on the rise. Machine learning is expected to have a crucial role in identifying retinal disease. Multiple medical institutions coope...
详细信息
As a classic semi-supervised approach, the Transductive Support Vector Machine (TSVM) has exhibited remarkable accuracy by utilizing unlabeled data. However, the robustness of TSVM against adversarial attacks remains ...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
As a classic semi-supervised approach, the Transductive Support Vector Machine (TSVM) has exhibited remarkable accuracy by utilizing unlabeled data. However, the robustness of TSVM against adversarial attacks remains a subject of investigation, prompting concerns about its reliability in security-critical applications. To unveil the vulnerability of TSVM, we introduce a finite-attack model specifically tailored to its characteristics, effectively manipulating its outputs. Additionally, we present Adversarial Defense-based TSVM (AD-TSVM), the first dedicated defense scheme designed for TSVM. AD-TSVM incorporates adversarial information into the optimization process, enhancing robustness by rebuilding a customized loss function and decision margin to counteract attacks. Rigorous experiments conducted on benchmark datasets demonstrate the effectiveness of AD-TSVM in significantly improving both the accuracy and stability of TSVM when confronted with adversarial attacks. This pioneering research assesses the weaknesses of TSVM and, more importantly, offers valuable insights and solutions for developing secure and trustworthy TSVM systems in the face of emerging threats.
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
Existing self-knowledge distillation (Self-KD) solutions usually focus on transferring historical predictions of individual instances to the current network. However, this approach tends to create overconfidence for e...
Existing self-knowledge distillation (Self-KD) solutions usually focus on transferring historical predictions of individual instances to the current network. However, this approach tends to create overconfidence for easy instances and underconfidence for hard instances. The widely used temperature-based strategies to smooth or sharpen the predicted distributions can lead to inconsistencies across instances, causing sensitivity issues. To address this, our approach views a queue of instances as an ensemble rather than treating each instance independently. We propose a novel method that distills historical knowledge from a dimensional perspective, utilizing intra class characteristics and interclass relationships within each ensemble. First, we align each dimension distribution from the current network to the historical output. Second, we ensure each dimension is closer to similar dimensions than dissimilar ones, maintaining consistent attitudes from present and historical perspectives. Our insights reveal that distilling historical knowledge from a dimensional perspective is more effective than the traditional instance-based approach, with potential applications in related tasks. Empirical results on three famous datasets and various network architectures demonstrate the superiority of our proposed method. Our code is available at https://***/WenkeHuang/DimSelfKD.
暂无评论