With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adver...
详细信息
Movable antennas (MAs) enhance flexibility in beamforming gain and interference suppression by adjusting position within certain areas of the transceivers. In this paper, we propose an MA-assisted integrated sensing a...
详细信息
Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs a...
详细信息
The conventional approach of choosing the best route to carry network traffic in wireless multi-hop networks does not maximize the overall network throughput and can lead to short-term instabilities in network state w...
详细信息
ISBN:
(数字)9798350350128
ISBN:
(纸本)9798350350135
The conventional approach of choosing the best route to carry network traffic in wireless multi-hop networks does not maximize the overall network throughput and can lead to short-term instabilities in network state with dire consequences. To date, wireless network route selection considers mainly network or link metrics, always picking the best links, thus channeling all packets through a subset of all availab.e links. This leaves weaker links under-utilized although such links can in fact be used to carry smaller packets or packets with less stringent requirements and free up bandwidth on the better links for larger packets or traffic with higher service requirements. As network traffic volume and heterogeneity increase in future networks, we need to maximize the usage of availab.e network bandwidth and distribute the network traffic load. We combine network link metrics and packet attributes to determine the successful packet transmission probability, and then use this outcome to pick suitable links to forward the packet, which is not necessarily the link with the best metric. To validate the efficacy of our proposed approach in routing performance and energy efficiency, we applied it in routing for wireless multi-hop networks. More importantly, we are able to spread the traffic across nodes in the network, thus achieving better network load-balancing and higher network resource utilization.
In order to achieve fast localization and detection of dog face in intelligent dog management system, a dog face detection algorithm based on improved Faster RCNN was proposed. To obtain the feature extraction backbon...
详细信息
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as ...
详细信息
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six
Based on the application requirements of the embedded Web server for external network access to the internal network, this paper designs and builds an embedded Web server scheme for external network access to the inte...
详细信息
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely...
ISBN:
(纸本)9798331314385
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is availab.e at https://***/Darkbblue/diffusion-content-shift.
Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension ...
暂无评论