2022 IEEE International Conference on Image Processing (ICIP)最新文献_第4页

CNN-Based Fast CU Partitioning Algorithm for VVC Intra Coding 基于cnn的VVC内编码快速CU划分算法

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897378

Jun Xu, Guoqing Wu, Chen Zhu, Yan Huang, Li Song

引用次数: 4

Adversarial Training with Channel Attention Regularization 信道注意正则化对抗性训练

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897754

Seungju Cho, Junyoung Byun, Myung-Joon Kwon, Yoon-Ji Kim, Changick Kim

{"title":"Adversarial Training with Channel Attention Regularization","authors":"Seungju Cho, Junyoung Byun, Myung-Joon Kwon, Yoon-Ji Kim, Changick Kim","doi":"10.1109/ICIP46576.2022.9897754","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897754","url":null,"abstract":"Adversarial attack shows that deep neural networks (DNNs) are highly vulnerable to small perturbation. Currently, one of the most effective ways to defend against adversarial attacks is adversarial training, which generates adversarial examples during training and induces the models to classify them correctly. To further increase robustness, various techniques such as exploiting additional unlabeled data and novel training loss have been proposed. In this paper, we propose a novel regularization method that exploits latent features, which can be easily combined with existing approaches. We discover that particular channels are more sensitive to adversarial perturbation, motivating us to propose regularizing these channels. Specifically, we attach a channel attention module for adjusting sensitivity of each channel by reducing the difference between the latent feature of the natural image and that of the adversarial image, which we call Channel Attention Regularization (CAR). CAR can be combined with the existing adversarial training framework, showing that it improves the robustness of state-of-the-art defense models. Experiments on various existing adversarial training methods against diverse attacks show the effectiveness of our methods. Codes are available at https://github.com/sgmath12/Adversarial-Training-CAR.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"33 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120873324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI-Based Compression: A New Unintended Counter Attack on JPEG-Related Image Forensic Detectors? 基于人工智能的压缩:对jpeg相关图像取证检测器的一种新的意外反击?

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897697

Alexandre Berthet, J. Dugelay

{"title":"AI-Based Compression: A New Unintended Counter Attack on JPEG-Related Image Forensic Detectors?","authors":"Alexandre Berthet, J. Dugelay","doi":"10.1109/ICIP46576.2022.9897697","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897697","url":null,"abstract":"The detection of forged images is an important topic in digital image forensics. There are two main types of forgery: copy-move and splicing. These forgeries are created with image editors that apply JPEG compression by default, when saving the forged images. As a result, the authentic and falsified areas have different compression statistics, including histograms of DCT coefficients that show inconsistencies in the case of double JPEG compression. Therefore, the detection of double JPEG compression (DJPEG-C) is an important topic for JPEG-related image forensic detectors. Since the emergence of deep learning in image processing, AI-based compression methods have been proposed. This paper is the first to consider AI-based compression with digital image analysis tools. The objective is to understand whether AI-based compression can be a new unintended counter-attack for JPEG-related image forensic detectors. To verify our hypothesis, we selected the best detector to date, an AI-based compression method and the Casia v2 database that contains both splicing and copy-move (all publicly available). We focused our experiment on benign post-processing operations: AI-based and JPEG recompressions (with different quality levels). The evaluation is performed using different metrics (average precision, F1 score and accuracy, PSNR, SSIM) to take into account both the impact on detection and image quality. At similar image quality, AI-based recompression achieves a decrease in performance at least twice higher than JPEG, while preserving high visual image quality. Thus, AI-based compression is a new unintended counter-attack, which can no longer be ignored in future studies on image forensic detectors.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121288141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

ICIP 2022 Organizing Committee ICIP 2022组委会

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/icip46576.2022.9897673

引用次数: 0

Maskformer with Improved Encoder-Decoder Module for Semantic Segmentation of Fine-Resolution Remote Sensing Images 基于改进编解码器模块的掩模器用于遥感图像的语义分割

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897888

Zhuoxuan Li, Junli Yang, Bin Wang, Yaqi Li, Ting Pan

{"title":"Maskformer with Improved Encoder-Decoder Module for Semantic Segmentation of Fine-Resolution Remote Sensing Images","authors":"Zhuoxuan Li, Junli Yang, Bin Wang, Yaqi Li, Ting Pan","doi":"10.1109/ICIP46576.2022.9897888","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897888","url":null,"abstract":"In 2021, the Transformer based models have demonstrated extraordinary achievement in the field of computer vision. Among which, Maskformer, a Transformer based model adopting the mask classification method, is an outstanding model in both semantic segmentation and instance segmentation. Considering the specific characteristics of semantic segmentation of remote sensing images (RSIs), we design CADA-MaskFormer(a Mask classification-based model with Cross-shaped window self-Attention and Densely connected feature Aggregation) based on Maskformer by improving its encoder and pixel decoder. Concretely, the mask classification that generates one or even more masks for specific category to perform the elaborate segmentation is especially suitable for handling the characteristic of large within-class and small between-class variance of RSIs. Furthermore, we apply the Cross-Shaped Window self-attention mechanism to model the long-range context information contained in RSIs at maximum extent without the increasing of computational complexity. In addition, the Densely Connected Feature Aggregation Module (DCFAM) is used as the pixel decoder to incorporate multi-level feature maps from the encoder to get a finer semantic segmentation map. Extensive experiments conducted on two remotely sensed semantic segmentation datasets Potsdam and Vaihingen achieves 91.88% and 91.01% in OA index respectively, outperforming most of competitive models designed for RSIs. The code is available from https://github.com/lqwrl542293/JL-Yang_CV/tree/master/CADA_Maskformer","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"569 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116253632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Diagnosing Autism Spectrum Disorder Using Ensemble 3D-CNN: A Preliminary Study 使用集成3D-CNN诊断自闭症谱系障碍:初步研究

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897628

Jingsheng Deng, Md Rakibul Hasan, Minhaz Mahmud, Ma Farsi Hasan, K. A. Ahmed, Md. Zakir Hossain

{"title":"Diagnosing Autism Spectrum Disorder Using Ensemble 3D-CNN: A Preliminary Study","authors":"Jingsheng Deng, Md Rakibul Hasan, Minhaz Mahmud, Ma Farsi Hasan, K. A. Ahmed, Md. Zakir Hossain","doi":"10.1109/ICIP46576.2022.9897628","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897628","url":null,"abstract":"Autism spectrum disorder (ASD) is a neuro-developmental disorder that results in behavioural retardation in verbal communications and social interactions. Traditional ASD detection methods involve assessing patients’ behavioural patterns by medical practitioners, which often lack credibility and precision. The contribution of the current study involves a 3D-CNN (convolutional neural network) model to diagnose ASD patients from healthy individuals using functional magnetic resonance imaging (fMRI) of the brain. We utilised a publicly available dataset, Autism Brain Imaging Data Exchange (ABIDE I), and tested different CNN-based models in individual and combined brain parcellations. Our model showed a better outcome (74.53% accuracy, 69.98% sensitivity, and 76.00% specificity) for combined parcellations than individuals. Further, we compared our model with several state-of-the-art models and discussed the suitability of our model for future prospects. The current model would be a predecessor of future prognosis models or behavioural patterns-based multi-modal models for early detection of ASD.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116346399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Multi-label Aerial Image Classification Based on Image-Specific Concept Graphs 基于图像特定概念图的多标签航空图像分类

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897476

Dan Lin, Zhikui Chen, Liang Zhao, Kai Wang

引用次数: 0

3DCT Reconstruction from a Single X-Ray Projection Using Convolutional Neural Network 利用卷积神经网络从单个x射线投影中重建3DCT

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897902

Estelle Loÿen, D. Dasnoy-Sumell, B. Macq

引用次数: 0

A Novel Rank Correlation Measure for Manifold Learning on Image Retrieval and Person Re-ID 一种新的基于图像检索和人物重新识别的流形学习秩相关测度

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9898060

Lucas Pascotti Valem, Vinicius Atsushi Sato Kawai, Vanessa Helena Pereira-Ferrero, D. C. G. Pedronette

引用次数: 0

Multi-View Feature Boosting Network for Deep Subspace Clustering 深度子空间聚类的多视图特征增强网络

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897575

Jinjoo Song, Gangjoon Yoon, Sangwon Baek, S. Yoon

引用次数: 0