检索结果-内蒙古大学图书馆

Survey on AI-Generated Media Detection: From Non-MLLM to MLLM

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zou, Yueying Li, Peipei Li, Zekun Huang, Huaibo Cui, Xing Liu, Xuannan Zhang, Chenghanyu He, Ran School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China School of Science Beijing University of Posts and Telecommunications Beijing100876 China School of Computer Science University of California Santa Barbara United States State Key Laboratory of Multimodal Artificial Intelligence Systems CASIA New Laboratory of Pattern Recognition CASIA School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China

The proliferation of AI-generated media poses significant challenges to information authenticity and social trust, making reliable detection methods highly demanded. Methods for detecting AI-generated media have evolved rapidly, paralleling the advancement of Multimodal Large Language Models (MLLMs). Current detection approaches can be categorized into two main groups: Non-MLLM-based and MLLM-based methods. The former employs high-precision, domain-specific detectors powered by deep learning techniques, while the latter utilizes general-purpose detectors based on MLLMs that integrate authenticity verification, explainability, and localization capabilities. Despite significant progress in this field, there remains a gap in literature regarding a comprehensive survey that examines the transition from domain-specific to general-purpose detection methods. This paper addresses this gap by providing a systematic review of both approaches, analyzing them from single-modal and multimodal perspectives. We present a detailed comparative analysis of these categories, examining their methodological similarities and differences. Through this analysis, we explore potential hybrid approaches and identify key challenges in forgery detection, providing direction for future research. Additionally, as MLLMs become increasingly prevalent in detection tasks, ethical and security considerations have emerged as critical global concerns. We examine the regulatory landscape surrounding Generative AI (GenAI) across various jurisdictions, offering valuable insights for researchers and practitioners in this field. © 2025, CC BY.

关键词： Adversarial machine learning

Reprogramming pretrained target-specific diffusion models for dual-target drug design 24

学校读者我要写书评

暂无评论

Reprogramming pretrained target-specific diffusion models fo...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiangxin Zhou Jiaqi Guan Yijia Zhang Xingang Peng Liang Wang Jianzhu Ma School of Artificial Intelligence University of Chinese Academy of Sciences and New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) Department of Computer Science University of Illinois Urbana-Champaign Department of Electronic Engineering Tsinghua University Institute for Artificial Intelligence Peking University Department of Electronic Engineering Tsinghua University and Institute for AI Industry Research Tsinghua University

ISBN: (纸本)9798331314385

Dual-target therapeutic strategies have become a compelling approach and attracted significant attention due to various benefits, such as their potential in overcoming drug resistance in cancer therapy. Considering the tremendous success that deep generative models have achieved in structure-based drug design in recent years, we formulate dual-target drug design as a generative task and curate a novel dataset of potential target pairs based on synergistic drug combinations. We propose to design dual-target drugs with diffusion models that are trained on single-target protein-ligand complex pairs. Specifically, we align two pockets in 3D space with protein-ligand binding priors and build two complex graphs with shared ligand nodes for SE(3)-equivariant composed message passing, based on which we derive a composed drift in both 3D and categorical probability space in the generative process. Our algorithm can well transfer the knowledge gained in single-target pretraining to dual-target scenarios in a zero-shot manner. We also repurpose linker design methods as strong baselines for this task. Extensive experiments demonstrate the effectiveness of our method compared with various baselines.

关键词：

Enhancing Sound Source Localization via False Negative Elimination

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Song, Zengjie Zhang, Jiangshe Wang, Yuxi Fan, Junsong Zhang, Zhaoxiang School of Mathematics and Statistics Xi'an Jiaotong University Xi'An710049 China Center for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong New Laboratory of Pattern Recognition State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, the common practice of randomly sampling negatives in prior arts can lead to the false negative issue, where the sounds semantically similar to visual instance are sampled as negatives and incorrectly pushed away from the visual anchor/query. As a result, this misalignment of audio and visual features could yield inferior performance. To address this issue, we propose a novel audio-visual learning framework which is instantiated with two individual learning schemes: self-supervised predictive learning (SSPL) and semantic-aware contrastive learning (SACL). SSPL explores image-audio positive pairs alone to discover semantically coherent similarities between audio and visual features, while a predictive coding module for feature alignment is introduced to facilitate the positive-only learning. In this regard SSPL acts as a negative-free method to eliminate false negatives. By contrast, SACL is designed to compact visual features and remove false negatives, providing reliable visual anchor and audio negatives for contrast. Different from SSPL, SACL releases the potential of audio-visual contrastive learning, offering an effective alternative to achieve the same goal. Comprehensive experiments demonstrate the superiority of our approach over the state-of-the-arts. Furthermore, we highlight the versatility of the learned representation by extending the approach to audio-visual event classification and object detection tasks. Code and models are available at: https://***/zjsong/SACL. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xie, Liangbin Wang, Xintao Chen, Xiangyu Li, Gen Shan, Ying Zhou, Jiantao Dong, Chao State Key Laboratory of Internet of Things for Smart City University of Macau China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China ARC Lab Tencent PCG China Shanghai Artificial Intelligence Laboratory China Platform Technologies China

Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable artifacts, especially in practical scenarios. Previous works typically suppress artifacts with an extra loss penalty in the training phase. They only work for in-distribution artifact types generated during training. When applied in real-world scenarios, we observe that those improved methods still generate obviously annoying artifacts during inference. In this paper, we analyze the cause and characteristics of the GAN artifacts produced in unseen test data without ground-truths. We then develop a novel method, namely, DeSRA, to Detect and then "Delete" those SR Artifacts in practice. Specifically, we propose to measure a relative local variance distance from MSE-SR results and GAN-SR results, and locate the problematic areas based on the above distance and semantic-aware thresholds. After detecting the artifact regions, we develop a finetune procedure to improve GAN-based SR models with a few samples, so that they can deal with similar types of artifacts in more unseen real data. Equipped with our DeSRA, we can successfully eliminate artifacts from inference and improve the ability of SR models to be applied in real-world scenarios. The code will be available at https://***/TencentARC/DeSRA. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Code is available at https://***/blgpb/FedIIH. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

Distinguishing Computer-Generated Images from Natural Images Using Channel and Pixel Correlation

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2020年第3期35卷 592-602页

作者： Rui-Song Zhang Wei-Ze Quan Lu-Bin Fan Li-Ming Hu Dong-Ming Yan National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Alibaba Group Hangzhou 310023China State Key Laboratory of Hydro-Science and Engineering Tsinghua UniversityBeijing 100084China

With the recent tremendous advances of computer graphics rendering and image editing technologies,computergenerated fake images,which in general do not reflect what happens in the reality,can now easily deceive the inspection of human visual *** this work,we propose a convolutional neural network(CNN)-based model to distinguish computergenerated(CG)images from natural images(NIs)with channel and pixel *** key component of the proposed CNN architecture is a self-coding module that takes the color images as input to extract the correlation between color channels *** previous approaches that directly apply CNN to solve this problem,we consider the generality of the network(or subnetwork),i.e.,the newly introduced hybrid correlation module can be directly combined with existing CNN models for enhancing the discrimination capacity of original *** results demonstrate that the proposed network outperforms state-of-the-art methods in terms of classification *** also show that the newly introduced hybrid correlation module can improve the classification accuracy of different CNN architectures.

关键词： natural image computer-generated image channel and pixel correlation convolutional neural network

Modeling Inter-Intra Heterogeneity for Graph Federated Learning 39

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learn...

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Federated learning

Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Haochen Shen, Yujun Fei, Jingjing Li, Wei Wu, Liwei Wang, Yuxi Zhang, Zhaoxiang New Laboratory of Pattern Recognition State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong Chinese University of Hong Kong Hong Kong SenseTime Research Beijing China

Domain-adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly learning categorically discriminative target features for segmenting target images, which is challenging in the absence of target labels. This work provides a new perspective. We observe that the features learned with source data manage to keep categorically discriminative during training, thereby enabling us to implicitly learn adequate target representations by simply pulling target features close to source features for each category. To this end, we propose T2S-DA, which encourages the model to learn similar cross-domain features. Also, considering the pixel categories are heavily imbalanced for segmentation datasets, we come up with a dynamic re-weighting strategy to help the model concentrate on those underperforming classes. Extensive experiments confirm that T2S-DA learns a more discriminative and generalizable representation, significantly surpassing the state-of-the-art. We further show that T2SDA is quite qualified for the domain generalization task, verifying its domain-invariant property. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

Activating More Pixels in Image Super-Resolution Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Xiangyu Wang, Xintao Zhou, Jiantao Qiao, Yu Dong, Chao State Key Laboratory of Internet of Things for Smart City University of Macau China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China ARC Lab Tencent PCG China

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels