2022 IEEE International Conference on Image Processing (ICIP)最新文献_第5页

Monitoring of Varroa Infestation Rate in Beehives: A Simple AI Approach 蜂箱中Varroa侵害率的监测:一种简单的AI方法

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897809

Lukáš Picek, Adam Novozámský, R. Frydrychová, B. Zitová, Pavel Mach

引用次数: 1

Multi-Step Test-Time Adaptation with Entropy Minimization and Pseudo-Labeling 基于熵最小化和伪标记的多步测试时间自适应

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897419

Hiroaki Kingetsu, Kenichi Kobayashi, Y. Okawa, Yasuto Yokota, K. Nakazawa

引用次数: 4

The Lifecycle of a Neural Network in the Wild: A Multiple Instance Learning Study on Cancer Detection from Breast Biopsies Imaged with Novel Technique 野外神经网络的生命周期:用新技术从乳腺活检图像中检测癌症的多实例学习研究

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897596

D. Mandache, E. B. Á. L. Guillaume, Y. Badachi, J. Olivo-Marin, V. Meas-Yedid

{"title":"The Lifecycle of a Neural Network in the Wild: A Multiple Instance Learning Study on Cancer Detection from Breast Biopsies Imaged with Novel Technique","authors":"D. Mandache, E. B. Á. L. Guillaume, Y. Badachi, J. Olivo-Marin, V. Meas-Yedid","doi":"10.1109/ICIP46576.2022.9897596","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897596","url":null,"abstract":"In the context of tissue examination for breast cancer assessment, we propose a label-free imaging based on Optical Coherence Tomography (OCT) signal combined with a multiple instance learning (MIL) model to respond to a critical need for fast at point-of-care diagnosis: biopsy or surgery time. This new imaging, Dynamic Cell Imaging (DCI), is the time-resolved variant of Full-Field OCT (FFOCT) and offers an intra-cellular resolution of about 1 micron, together with optical sectioning and an improved cell contrast. In order to tackle the challenges of limited data and annotations, while remaining in the scope of interpretability, we design an instance-level MIL model with a focus on adapted data sampling. The interest of this method is that it incorporates task-specific feature learning and also produces instance predictions. For a dataset of 150 core-needle biopsies, we achieve a considerable improvement of more than 20 percentage points in specificity and about 10 in accuracy by leveraging intra-domain (as compared to extra-domain) pre-training.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"28 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":"115810772","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

Background-Tolerant Object Classification With Embedded Segmentation Mask For Infrared And Color Imagery 基于嵌入式分割掩模的红外和彩色图像背景容忍目标分类

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897418

Maliha Arif, Calvin Yong, Abhijit Mahalanobis, N. Rahnavard

{"title":"Background-Tolerant Object Classification With Embedded Segmentation Mask For Infrared And Color Imagery","authors":"Maliha Arif, Calvin Yong, Abhijit Mahalanobis, N. Rahnavard","doi":"10.1109/ICIP46576.2022.9897418","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897418","url":null,"abstract":"Even though convolutional neural networks (CNNs) can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that networks often learn background textures, which are not relevant to the object of interest. In turn this makes the networks susceptible to variations and changes in the background which may negatively affect their performance.We propose a new three-step training procedure called split training to reduce this bias in CNNs for object recognition using Infrared imagery and Color (RGB) data. Our split training procedure has three steps. First, a baseline model is trained to recognize objects in images without background, and the activations produced by the higher layers are observed. Next, a second network is trained using Mean Square Error (MSE) loss to produce the same activations, but in response to the objects embedded in background. This forces the second network to ignore the background while focusing on the object of interest. Finally, with layers producing the activations frozen, the rest of the second network is trained using cross-entropy loss to classify the objects in images with background. Our training method outperforms the traditional training procedure in both a simple CNN architecture, as well as for deep CNNs like VGG and DenseNet, and learns to mimic human vision which focuses more on shape and structure than background with higher accuracy.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":" 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":"132075162","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

Few-Shot Learning Network for Moving Object Detection Using Exemplar-Based Attention Map 基于样例注意图的运动目标检测少镜头学习网络

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897894

Islam I. Osman, M. Shehata

引用次数: 3

Towards Lightweight Neural Network-based Chroma Intra Prediction for Video Coding 基于神经网络的视频编码色度内预测研究

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897708

Chengyi Zou, Shuai Wan, M. Mrak, M. G. Blanch, Luis Herranz, Tiannan Ji

引用次数: 0

ICIP 2022 Challenge: PEDCMI, TOOD Enhanced by Slicing-Aided Fine-Tuning and Inference ICIP 2022挑战:通过切片辅助微调和推理增强的PEDCMI, ood

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897826

Alžběta Turečková, Tomáš Tureček, Z. Oplatková

引用次数: 0

Channel-Position Self-Attention with Query Refinement Skeleton Graph Neural Network in Human Pose Estimation 基于查询细化骨架图神经网络的通道位置自关注人体姿态估计

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897882

Shek Wai Chu, Chaoyi Zhang, Yang Song, Weidong (Tom) Cai

引用次数: 0

Detection-Identification Balancing Margin Loss for One-Stage Multi-Object Tracking 单阶段多目标跟踪的检测-识别平衡裕度损失

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9898030

Heansung Lee, Suhwan Cho, Sungjun Jang, Jungho Lee, Sungmin Woo, Sangyoun Lee

{"title":"Detection-Identification Balancing Margin Loss for One-Stage Multi-Object Tracking","authors":"Heansung Lee, Suhwan Cho, Sungjun Jang, Jungho Lee, Sungmin Woo, Sangyoun Lee","doi":"10.1109/ICIP46576.2022.9898030","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9898030","url":null,"abstract":"In recent years, one-stage multi-object tracking (MOT) methods, which jointly learn detection and identification in a single network, have attracted extensive attention, due to their efficiency. However, the negative transfer effects caused by the two conflicting objectives of detection and identification have rarely been explored. In this paper, we propose a Detection-Identification Balancing Margin (DIM) loss for minimizing the adverse effects caused by these two different objectives. The proposed DIM loss consists of Detection Margin (DM) loss and Identification Margin (IM) loss. DM loss forces features that are farther from the center of the foreground features than the defined margin due to identification learning to be converged to ensure accurate detection. IM loss enables the various feature representations that are essential for identification by intentionally spreading features that become overly clustered due to detection learning. The proposed DIM loss demonstrates competitive and balanced performance for MOT by providing a positive transfer for features that had a strong negative impact on detection and identification, respectively. (HOTA 61.5, MOTA 75.3, IDF1 75.6 on MOT16, and real-time rates of 25.9 fps were achieved)","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"1 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":"134377863","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

Viewport-Oriented Panoramic Image Inpainting 面向viewport的全景图像绘制

2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897208

Zhuoyi Shang, Yanwei Liu, Guoyi Li, Yunjian Zhang, Jingbo Miao, Jinxia Liu, Liming Wang

引用次数: 0