2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)最新文献_第2页

FedAffect: Few-shot federated learning for facial expression recognition FedAffect:用于面部表情识别的少量联邦学习

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00463

Debaditya Shome, Tejaswini Kar

{"title":"FedAffect: Few-shot federated learning for facial expression recognition","authors":"Debaditya Shome, Tejaswini Kar","doi":"10.1109/ICCVW54120.2021.00463","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00463","url":null,"abstract":"Annotation of large-scale facial expression datasets in the real world is a major challenge because of privacy concerns of the individuals due to which traditional supervised learning approaches won’t scale. Moreover, training models on large curated datasets often leads to dataset bias which reduces generalizability for real world use. Federated learning is a recent paradigm for training models collaboratively with decentralized private data on user devices. In this paper, we propose a few-shot federated learning framework which utilizes few samples of labeled private facial expression data to train local models in each training round and aggregates all the local model weights in the central server to get a globally optimal model. In addition, as the user devices are a large source of unlabeled data, we design a federated learning based self-supervised method to disjointly update the feature extractor network on unlabeled private facial data in order to learn robust and diverse face representations. Experimental results by testing the globally trained model on benchmark datasets (FER-2013 and FERG) show comparable performance with state of the art centralized approaches. To the best of author’s knowledge, this is the first work on few-shot federated learning for facial expression recognition.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126857233","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: 15

MANet: a Motion-Driven Attention Network for Detecting the Pulse from a Facial Video with Drastic Motions 一种动作驱动的注意网络，用于检测具有剧烈动作的面部视频的脉冲

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00270

Xuenan Liu, Xuezhi Yang, Ziyan Meng, Ye Wang, J Zhang, Alexander Wong

引用次数: 2

Simple Baseline for Single Human Motion Forecasting 单一人体运动预测的简单基线

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00255

Chenxi Wang, Yunfeng Wang, Zixuan Huang, Zhiwen Chen

引用次数: 14

Hyperspectral 3D Mapping of Underwater Environments 水下环境的高光谱3D映射

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00413

Maxime Ferrera, A. Arnaubec, K. Istenič, N. Gracias, T. Bajjouk

{"title":"Hyperspectral 3D Mapping of Underwater Environments","authors":"Maxime Ferrera, A. Arnaubec, K. Istenič, N. Gracias, T. Bajjouk","doi":"10.1109/ICCVW54120.2021.00413","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00413","url":null,"abstract":"Hyperspectral imaging has been increasingly used for underwater survey applications over the past years. As many hyperspectral cameras work as push-broom scanners, their use is usually limited to the creation of photo-mosaics based on a flat surface approximation and by interpolating the camera pose from dead-reckoning navigation. Yet, because of drift in the navigation and the mostly wrong flat surface assumption, the quality of the obtained photo-mosaics is often too low to support adequate analysis. In this paper we present an initial method for creating hyper-spectral 3D reconstructions of underwater environments. By fusing the data gathered by a classical RGB camera, an inertial navigation system and a hyperspectral push- broom camera, we show that the proposed method creates highly accurate 3D reconstructions with hyperspectral textures. We propose to combine techniques from simultaneous localization and mapping, structure-from-motion and 3D reconstruction and advantageously use them to create 3D models with hyperspectral texture, allowing us to overcome the flat surface assumption and the classical limitation of dead-reckoning navigation.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122299229","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: 6

The Aircraft Context Dataset: Understanding and Optimizing Data Variability in Aerial Domains 飞机背景数据集:理解和优化航空领域的数据变异性

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00426

Daniel Steininger, Verena Widhalm, Julia Simon, A. Kriegler, Christoph Sulzbacher

引用次数: 3

Student-Teacher Oneness: A Storage-efficient approach that improves facial expression recognition 师生合一:提高面部表情识别的高效存储方法

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00453

Zhenzhu Zheng, C. Rasmussen, Xi Peng

{"title":"Student-Teacher Oneness: A Storage-efficient approach that improves facial expression recognition","authors":"Zhenzhu Zheng, C. Rasmussen, Xi Peng","doi":"10.1109/ICCVW54120.2021.00453","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00453","url":null,"abstract":"We present Student-Teacher Oneness (STO), a simple but effective approach for online knowledge distillation improves facial expression recognition, without introducing any extra model parameters. Stochastic sub-networks are designed to replace the multi-branch architecture component in current online distillation methods. This leads to a simplified architecture, and yet competitive performances. Under the \"teacher-student\" framework, we construct both teacher and student within the same target network. Student network is the sub-networks which randomly skipping some portions of the full (target) network. The teacher network is the full network, can be considered as the ensemble of all possible student networks. The training process is performed in a closed-loop: (1) Forward prediction contains two passes that generate student and teacher predictions. (2) Backward distillation allows knowledge transfer from the teacher back to students. Comprehensive evaluations show that STO improves the generalization ability of a variety of deep neural networks to a significant margin. The results prove our superior performance in facial expression recognition task on FER-2013 and RAF.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122720280","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: 1

Efficient Search in a Panoramic Image Database for Long-term Visual Localization 面向长期视觉定位的全景图像数据库的高效搜索

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00198

Semih Orhan, Y. Bastanlar

引用次数: 5

Coarse-grained Density Map Guided Object Detection in Aerial Images 航空图像中粗粒度密度图引导目标检测

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00313

Chengzhen Duan, Zhiwei Wei, Chi Zhang, Siying Qu, Hongpeng Wang

{"title":"Coarse-grained Density Map Guided Object Detection in Aerial Images","authors":"Chengzhen Duan, Zhiwei Wei, Chi Zhang, Siying Qu, Hongpeng Wang","doi":"10.1109/ICCVW54120.2021.00313","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00313","url":null,"abstract":"Object detection in aerial images is challenging for at least two reasons: (1) most objects are small scale relative to high resolution aerial images; and (2) the object position distribution is nonuniform, making the detection inefficient. In this paper, a novel network, the coarse-grained density map network (CDMNet), is proposed to address these problems. Specifically, we format density maps into coarsegrained form and design a lightweight dual task density estimation network. The coarse-grained density map can not only describe the distribution of objects, but also cluster objects, quantify scale and reduce computing. In addition, we propose a cluster region generation algorithm guided by density maps to crop input images into multiple subregions, denoted clusters, where the objects are adjusted in a reasonable scale. Besides, we improved mosaic data augmentation to relieve foreground-background and category imbalance problems during detector training. Evaluated on two popular aerial datasets, VisDrone[29] and UAVDT[6], CDMNet has achieved significant accuracy improvement compared with previous state-of-the-art methods.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122485966","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: 18

Graph Cuts Loss to Boost Model Accuracy and Generalizability for Medical Image Segmentation 图切割损失提高医学图像分割模型的准确性和可泛化性

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00369

Zhou Zheng, M. Oda, K. Mori

{"title":"Graph Cuts Loss to Boost Model Accuracy and Generalizability for Medical Image Segmentation","authors":"Zhou Zheng, M. Oda, K. Mori","doi":"10.1109/ICCVW54120.2021.00369","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00369","url":null,"abstract":"Segmentation accuracy and generalization ability are essential for deep learning models, especially in medical image segmentation. We present a novel, robust yet straightforward loss function to boost model accuracy and generalizability for medical image segmentation. We reformulate the graph cuts cost function to a loss function for supervised learning. The graph cuts loss innately focuses on a dual penalty to optimize the regional properties and boundary regularization. We benchmark the proposed loss on six public retinal vessel segmentation datasets with a comprehensive intra-dataset and cross-dataset evaluation. Results reveal that the proposed loss is more generalizable, narrowing the performance gap between different architectures. Besides, models trained with our loss show higher segmentation accuracy and better generalization ability than those trained with other mainstream losses. Moreover, we extend our loss to other segmentation tasks, e.g., left atrium and liver tumor segmentation. The proposed loss still achieves comparable performance to the state-of-the-art, demonstrating its potential for any N-D segmentation problem. The code is available at https://github.com/zzh_enggit/graphcutsloss.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114268166","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

Estimating Heart Rate from Unlabelled Video 从未标记的视频估计心率

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00307

John Gideon, Simon Stent

引用次数: 10