Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders(VAEs) is a popular strategy for generalized zero-shot learning(GZSL). However, due to the lac...
详细信息
Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders(VAEs) is a popular strategy for generalized zero-shot learning(GZSL). However, due to the lack of fine-grained instance-wise annotations, existing VAE methods can easily suffer from the posterior collapse problem. In this paper, we propose an innovative asymmetric VAE network by aligning enhanced feature representation(AEFR) for GZSL. Distinguished from general VAE structures, we designed two asymmetric encoders for visual and semantic observations and one decoder for visual reconstruction. Specifically, we propose a simple yet effective gated attention mechanism(GAM) in the visual encoder for enhancing the information interaction between observations and latent variables, alleviating the possible posterior collapse problem effectively. In addition, we propose a novel distributional decoupling-based contrastive learning(D2-CL) to guide learning classification-relevant information while aligning the representations at the taxonomy level in the latent representation space. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method. The source code is available at https://***/seeyourmind/AEFR.
Named in-network computing service (NICS) is a potential computing paradigm emerged recently. Benefitted from the characteristics of named addressing and routing, NICS can be flexibly deployed on NDN router side and p...
详细信息
Large-scale neural networks-based federated learning(FL)has gained public recognition for its effective capabilities in distributed ***,the open system architecture inherent to federated learning systems raises concer...
详细信息
Large-scale neural networks-based federated learning(FL)has gained public recognition for its effective capabilities in distributed ***,the open system architecture inherent to federated learning systems raises concerns regarding their vulnerability to potential *** attacks turn into a major menace to federated learning on account of their concealed property and potent destructive *** altering the local model during routine machine learning training,attackers can easily contaminate the global *** detection and aggregation solutions mitigate certain threats,but they are still insufficient to completely eliminate the influence generated by ***,federated unlearning that can remove unreliable models while maintaining the accuracy of the global model has become a *** some existing federated unlearning approaches are rather difficult to be applied in large neural network models because of their high computational ***,we propose SlideFU,an efficient anti-poisoning attack federated unlearning *** primary concept of SlideFU is to employ sliding window to construct the training process,where all operations are confined within the *** design a malicious detection scheme based on principal component analysis(PCA),which calculates the trust factors between compressed models in a low-cost way to eliminate unreliable *** confirming that the global model is under attack,the system activates the federated unlearning process,calibrates the gradients based on the updated direction of the calibration *** on two public datasets demonstrate that our scheme can recover a robust model with extremely high efficiency.
Computing-aware routing is the core technology of Computing Power Network. Through independently determining the forwarding target in each router, computingaware routing aims at scheduling the computing task to an opt...
详细信息
This paper presents a design method to implement an antenna array characterized by ultra-wide beam coverage,low profile,and low Sidelobe Level(SLL)for the application of Unmanned Aerial Vehicle(UAV)air-to-ground *** a...
详细信息
This paper presents a design method to implement an antenna array characterized by ultra-wide beam coverage,low profile,and low Sidelobe Level(SLL)for the application of Unmanned Aerial Vehicle(UAV)air-to-ground *** array consists of ten broadside-radiating,ultrawide-beamwidth elements that are cascaded by a central-symmetry series-fed network with tapered currents following Dolph-Chebyshev distribution to provide low ***,an innovative design of end-fire Huygens source antenna that is compatible with metal ground is presented.A low-profile,half-mode Microstrip Patch Antenna(MPA)is utilized to serve as the magnetic dipole and a monopole is utilized to serves as the electric dipole,constructing the compact,end-fire,grounded Huygens source ***,two opposite-oriented end-fire Huygens source antennas are seamlessly integrated into a single antenna element in the form of monopole-loaded MPA to accomplish the ultrawide,broadside-radiating *** consideration has been applied into the design of series-fed network as well as antenna element to compensate the adverse coupling effects between elements on the radiation *** indicates an ultrawide Half-Power Beamwidth(HPBW)of 161°and a low SLL of-25 dB with a high gain of 12 d Bi under a single-layer *** concurrent ultrawide beamwidth and low SLL make it particularly attractive for applications of UAV air-to-ground communication.
Open-vocabulary object detection (OVD) models are considered to be Large Multi-modal Models (LMM), due to their extensive training data and a large number of parameters. Mainstream OVD models prioritize object coarse-...
详细信息
As an effective method for data dimensionality reduction, feature selection could improve the classification accuracy and reduce the computational cost when dealing with high-dimensional data. Feature selection is ess...
详细信息
Advanced Driver Assistance Systems (ADAS) are designed to prevent collisions, identify the condition of drivers while operating vehicles, and provide additional information to enhance drivers' awareness of potenti...
详细信息
The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the...
详细信息
The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.
As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention...
详细信息
As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.
暂无评论