2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)最新文献_第3页

BRCars: a Dataset for Fine-Grained Classification of Car Images BRCars:用于汽车图像细粒度分类的数据集

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00039

Daniel M. Kuhn, V. Moreira

{"title":"BRCars: a Dataset for Fine-Grained Classification of Car Images","authors":"Daniel M. Kuhn, V. Moreira","doi":"10.1109/sibgrapi54419.2021.00039","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00039","url":null,"abstract":"Fine-grained computer vision tasks refer to the ability of distinguishing objects that belong to the same parent class, differentiating themselves by subtle visual elements. Image classification in car models is considered a fine-grained classification task. In this work, we introduce BRCars, a dataset that seeks to replicate the main challenges inherent to the task of classifying car images in many practical applications. BRCars contains around 300K images collected from a Brazilian car advertising website. The images correspond to 52K car instances and are distributed among 427 different models. The images are both from the exterior and the interior of the cars and present an unbalanced distribution across the different models. In addition, they are characterized by a lack of standardization in terms of perspective. We adopted a semi-automated annotation pipeline with the help of the new CLIP neural network, which enabled distinguishing thousands of images among different perspectives using textual queries. Experiments with standard deep learning classifiers were performed to serve as baseline results for future work on this topic. BRCars dataset is available at https://github.com/danimtk/brcars-dataset.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"6 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":"125565860","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

Learning-based End-to-End Video Compression Using Predictive Coding 基于学习的端到端视频压缩预测编码

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00030

Matheus C. de Oliveira, L. Martins, H. C. Jung, Nilson Donizete Guerin Júnior, R. C. D. Silva, Eduardo Peixoto, B. Macchiavello, E. Hung, Vanessa Testoni, P. Freitas

{"title":"Learning-based End-to-End Video Compression Using Predictive Coding","authors":"Matheus C. de Oliveira, L. Martins, H. C. Jung, Nilson Donizete Guerin Júnior, R. C. D. Silva, Eduardo Peixoto, B. Macchiavello, E. Hung, Vanessa Testoni, P. Freitas","doi":"10.1109/sibgrapi54419.2021.00030","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00030","url":null,"abstract":"Driven by the growing demand for video applications, deep learning techniques have become alternatives for implementing end-to-end encoders to achieve applicable compression rates. Conventional video codecs exploit both spatial and temporal correlation. However, due to some restrictions (e.g. computational complexity), they are commonly limited to linear transformations and translational motion estimation. Autoencoder models open up the way for exploiting predictive end-to-end video codecs without such limitations. This paper presents an entire learning-based video codec that exploits spatial and temporal correlations. The presented codec extends the idea of P-frame prediction presented in our previous work. The architecture adopted for I-frame coding is defined by a variational autoencoder with non-parametric entropy modeling. Besides an entropy model parameterized by a hyperprior, the inter-frame encoder architecture has two other independent networks, responsible for motion estimation and residue prediction. Experimental results indicate that some improvements still have to be incorporated into our codec to overcome the all-intra coding set up regarding the traditional algorithms High Efficiency Video Coding (HEVC) and Versatile Video Coding (VVC).","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"219 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":"115978409","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

Entropic Laplacian eigenmaps for unsupervised metric learning 无监督度量学习的熵拉普拉斯特征映射

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00049

A. Levada, M. Haddad

引用次数: 0

ConformalLayers: A non-linear sequential neural network with associative layers 共形层:具有关联层的非线性序列神经网络

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/SIBGRAPI54419.2021.00059

E. V. Sousa, Leandro A. F. Fernandes, C. Vasconcelos

引用次数: 3

A Deep Learning-based Approach for Tree Trunk Segmentation 基于深度学习的树干分割方法

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00057

D. Jodas, S. Brazolin, T. Yojo, Reinaldo Araujo de Lima, G. Velasco, A. Machado, J. Papa

{"title":"A Deep Learning-based Approach for Tree Trunk Segmentation","authors":"D. Jodas, S. Brazolin, T. Yojo, Reinaldo Araujo de Lima, G. Velasco, A. Machado, J. Papa","doi":"10.1109/sibgrapi54419.2021.00057","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00057","url":null,"abstract":"Recently, the real-time monitoring of the urban ecosystem has raised the attention of many municipal forestry management services. The proper maintenance of trees is seen as crucial to guarantee the quality and safety of the streetscape. However, the current analysis still involves the time-consuming fieldwork conducted for extracting the measurements of each part of the tree, including the angle and diameter of the trunk, to cite a few. Therefore, real-time monitoring is thoroughly necessary for the rapid identification of the constituent parts of the trees in images of the urban environment and the automatic estimation of their physical measures. This paper presents a method to segment the tree trunks in photographs of the municipal regions. To accomplish such a task, we introduce a semantic segmentation convolutional neural network architecture that incorporates a depthwise residual block to the well-known U-Net model to reduce the parameters required to create the network. Then, we perform a post-processing step to refine the segmented regions by removing the additional binary areas not related to the tree trunk. Lastly, the proposed method also extracts the central line of the identified region for future computation of the trunk measurements. Compared with the original U-Net architecture, the obtained results confirm the robustness of the proposed approaches, including similar evaluation metrics and the significant reduction of the network size.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"63 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":"131611514","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

GCOOD: A Generic Coupled Out-of-Distribution Detector for Robust Classification 一种用于鲁棒分类的通用耦合分布外检测器

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00062

Rogerio Ferreira De Moraes, Raphael S. Evangelista, Leandro A. F. Fernandes, Luis Martí

{"title":"GCOOD: A Generic Coupled Out-of-Distribution Detector for Robust Classification","authors":"Rogerio Ferreira De Moraes, Raphael S. Evangelista, Leandro A. F. Fernandes, Luis Martí","doi":"10.1109/sibgrapi54419.2021.00062","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00062","url":null,"abstract":"Neural networks have achieved high degrees of accuracy in classification tasks. However, when an out-of-distribution (OOD) sample (i.e., entries from unknown classes) is submitted to the classification process, the result is the association of the sample to one or more of the trained classes with different degrees of confidence. If any of these confidence values are more significant than the user-defined threshold, the network will mislabel the sample, affecting the model credibility. The definition of the acceptance threshold itself is a sensitive issue in the face of the classifier’s overconfidence. This paper presents the Generic Coupled OOD Detector (GCOOD), a novel Convolutional Neural Network (CNN) tailored to detect whether an entry submitted to a trained classification model is an OOD sample for that model. From the analysis of the Softmax output of any classifier, our approach can indicate whether the resulting classification should be considered or not as a sample of some of the trained classes. To train our CNN, we had to develop a novel training strategy based on Voronoi diagrams of the location of representative entries in the latent space of the classification model and graph coloring. We evaluated our approach using ResNet, VGG, DenseNet, and SqueezeNet classifiers with images from the CIFAR-10 dataset.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"5 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":"123909002","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

Bias and Fairness in Face Detection 人脸检测中的偏见与公平性

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00041

Hanna F. Menezes, Arthur S. C. Ferreira, E. Pereira, H. M. Gomes

{"title":"Bias and Fairness in Face Detection","authors":"Hanna F. Menezes, Arthur S. C. Ferreira, E. Pereira, H. M. Gomes","doi":"10.1109/sibgrapi54419.2021.00041","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00041","url":null,"abstract":"Processing of face images is used in many areas, for example: commercial applications such as video-games; facial biometrics; facial expression recognition, etc. Face detection is a crucial step for any system that processes face images. Therefore, if there is bias or unfairness in this first step, all the processing steps that follow may be compromised. Errors in automatic face detection may be harmful to people as, for instance, in situations where a decision may limit or restrict their freedom to come and go. Therefore, it is crucial to investigate the existence of these errors caused due to bias or unfairness. In this paper, an analysis of five well-known top accuracy face detectors is performed to investigate the presence of bias and unfairness in their results. Some of the metrics used to identify the existence of bias and unfairness involved the verification of demographic parity, verification of existence of false positives and/or false negatives, rate of positive prediction, and verification of equalized odds. Data from about 365 different individuals were randomly selected from the Facebook Casual Conversations Dataset, resulting in approximately 5,500 videos, providing 550,000 frames used for face detection in the performed experiments. The obtained results show that all five face detectors presented a high risk of not detecting faces from the female gender and from people between 46 and 85 years old. Furthermore, the skin tone groups related with dark skin are the groups pointed out with highest risk of faces not being detected for four of the five evaluated face detectors. This paper points out the necessity of the research community to engage in breaking the perpetuation of injustice that may be present in datasets or machine learning models.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"113 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":"124156747","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: 5

Analyzing the Effects of Dimensionality Reduction for Unsupervised Domain Adaptation 降维对无监督域自适应的影响分析

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00019

Renato Sergio Lopes Junior, W. R. Schwartz

引用次数: 0

SGAT: Semantic Graph Attention for 3D human pose estimation 基于语义图的三维人体姿态估计

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00042

L. Schirmer, Djalma Lúcio, Leandro Cruz, Alberto Barbosa Raposo, L. Velho, H. Lopes

引用次数: 0

An approach based on image processing techniques to segment lung region in chest X-ray images 基于图像处理技术的胸部x线图像肺区域分割方法

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/SIBGRAPI54419.2021.00024

Luiza C. de Menezes, Augusto R. V. F. de Araújo, A. Conci

引用次数: 1