2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)最新文献_第6页

Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers 通过领域对齐层提高领域自适应网络的可移植性

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-09-06 DOI: 10.1109/SIBGRAPI54419.2021.00031

Lucas Fernando Alvarenga e Silva, D. C. G. Pedronette, F. Faria, J. Papa, J. Almeida

{"title":"Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers","authors":"Lucas Fernando Alvarenga e Silva, D. C. G. Pedronette, F. Faria, J. Papa, J. Almeida","doi":"10.1109/SIBGRAPI54419.2021.00031","DOIUrl":"https://doi.org/10.1109/SIBGRAPI54419.2021.00031","url":null,"abstract":"Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the well-known domain shift problem. Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. However, most works conduct domain adaptation leveraging only the extracted features and reducing their domain shift from the perspective of loss function designs. In this paper, we argue that it is not sufficient to handle domain shift only based on domain-level features, but it is also essential to align such information on the feature space. Unlike previous works, we focus on the network design and propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. These layers are designed to match the feature distributions between different domains and can be easily applied to various MSDA methods. To show the robustness of our approach, we conducted an extensive experimental evaluation considering two challenging scenarios: digit recognition and object classification. The experimental results indicated that our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"307 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123066616","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

ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation ChessMix:用于遥感语义分割的空间上下文数据增强

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-08-26 DOI: 10.1109/SIBGRAPI54419.2021.00045

M. B. Pereira, J. A. D. Santos

{"title":"ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation","authors":"M. B. Pereira, J. A. D. Santos","doi":"10.1109/SIBGRAPI54419.2021.00045","DOIUrl":"https://doi.org/10.1109/SIBGRAPI54419.2021.00045","url":null,"abstract":"Labeling semantic segmentation datasets is a costly and laborious process if compared with tasks like image classification and object detection. This is especially true for remote sensing applications that not only work with extremely high spatial resolution data but also commonly require the knowledge of experts of the area to perform the manual labeling. Data augmentation techniques help to improve deep learning models under the circumstance of few and imbalanced labeled samples. In this work, we propose a novel data augmentation method focused on exploring the spatial context of remote sensing semantic segmentation. This method, ChessMix, creates new synthetic images from the existing training set by mixing transformed mini-patches across the dataset in a chessboard-like grid. ChessMix prioritizes patches with more examples of the rarest classes to alleviate the imbalance problems. The results in three diverse well-known remote sensing datasets show that this is a promising approach that helps to improve the networks’ performance, working especially well in datasets with few available data. The results also show that ChessMix is capable of improving the segmentation of objects with few labeled pixels when compared to the most common data augmentation methods widely used.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123083858","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

STN PLAD: A Dataset for Multi-Size Power Line Assets Detection in High-Resolution UAV Images STN PLAD:高分辨率无人机图像中多尺度电力线资产检测数据集

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-08-18 DOI: 10.1109/sibgrapi54419.2021.00037

A. Silva, H. Felix, T. Chaves, Francisco Simões, V. Teichrieb, Michel Mozinho dos Santos, H. Santiago, V. Sgotti, H. B. D. T. L. Neto

{"title":"STN PLAD: A Dataset for Multi-Size Power Line Assets Detection in High-Resolution UAV Images","authors":"A. Silva, H. Felix, T. Chaves, Francisco Simões, V. Teichrieb, Michel Mozinho dos Santos, H. Santiago, V. Sgotti, H. B. D. T. L. Neto","doi":"10.1109/sibgrapi54419.2021.00037","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00037","url":null,"abstract":"Many power line companies are using UAVs to perform their inspection processes instead of putting their workers at risk by making them climb high voltage power line towers, for instance. A crucial task for the inspection is to detect and classify assets in the power transmission lines. However, public data related to power line assets are scarce, preventing a faster evolution of this area. This work proposes the STN Power Line Assets Dataset, containing high-resolution and real-world images of multiple high-voltage power line components. It has 2,409 annotated objects divided into five classes: transmission tower, insulator, spacer, tower plate, and Stockbridge damper, which vary in size (resolution), orientation, illumination, angulation, and background. This work also presents an evaluation with popular deep object detection methods and MS-PAD, a new pipeline for detecting power line assets in hi-res UAV images. The latter outperforms the other methods achieving 89.2% mAP, showing considerable room for improvement. The STN PLAD dataset is publicly available at https://github.com/andreluizbvs/PLAD.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115338215","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: 8

Learning to Segment Medical Images from Few-Shot Sparse Labels 学习从少镜头稀疏标签分割医学图像

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-08-12 DOI: 10.1109/sibgrapi54419.2021.00021

P. H. T. Gama, H. Oliveira, J. A. D. Santos

引用次数: 3

Domain Adaptation for Holistic Skin Detection 面向整体皮肤检测的领域自适应

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-03-16 DOI: 10.1109/sibgrapi54419.2021.00056

Aloisio Dourado, Frederico Guth, T. D. Campos, Weigang Li

引用次数: 12