2022 19th Conference on Robots and Vision (CRV)最新文献

筛选

英文中文

Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos 基于监督对比学习的多模态视频异常驾驶行为检测

2022 19th Conference on Robots and Vision (CRV) Pub Date : 2021-09-09 DOI: 10.1109/CRV55824.2022.00011

Shehroz S. Khan, Ziting Shen, Haoying Sun, Ax Patel, A. Abedi

{"title":"Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos","authors":"Shehroz S. Khan, Ziting Shen, Haoying Sun, Ax Patel, A. Abedi","doi":"10.1109/CRV55824.2022.00011","DOIUrl":"https://doi.org/10.1109/CRV55824.2022.00011","url":null,"abstract":"Distracted driving is one of the major reasons for vehicle accidents. Therefore, detecting distracted driving behaviours is of paramount importance to reduce the millions of deaths and injuries occurring worldwide. Distracted or anomalous driving behaviours are deviations from ‘normal’ driving that need to be identified correctly to alert the driver. However, these driving behaviours do not comprise one specific type of driving style and their distribution can be different during the training and test phases of a classifier. We formulate this problem as a supervised contrastive learning approach to learn a visual representation to detect normal, and seen and unseen anomalous driving behaviours. We made a change to the standard contrastive loss function to adjust the similarity of negative pairs to aid the optimization. Normally, in a (self) supervised contrastive framework, the projection head layers are omitted during the test phase as the encoding layers are considered to contain general visual representative information. However, we assert that for a video-based supervised contrastive learning task, including a projection head can be beneficial. We showed our results on a driver anomaly detection dataset that contains 783 minutes of video recordings of normal and anomalous driving behaviours of 31 drivers from various top and front cameras (both depth and infrared). We also performed an extra step of fine tuning the labels in this dataset. Out of 9 video modalities combinations, our proposed contrastive approach improved the ROC AUC on 6 in comparison to the baseline models (from 4.23% to 8.9 1% for different modalities). We performed statistical tests that showed evidence that our proposed method performs better than the baseline contrastive learning setup. Finally, the results showed that the fusion of depth and infrared modalities from top and front view achieved the best AUC ROC of 0.9738 and AUC PR of 0.9772.","PeriodicalId":131142,"journal":{"name":"2022 19th Conference on Robots and Vision (CRV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130819554","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

Multiple Classifiers Based Adversarial Training for Unsupervised Domain Adaptation 基于多分类器的无监督域自适应对抗训练

2022 19th Conference on Robots and Vision (CRV) Pub Date : 2021-08-02 DOI: 10.1109/CRV55824.2022.00014

Yiju Yang, Taejoon Kim, Guanghui Wang

{"title":"Multiple Classifiers Based Adversarial Training for Unsupervised Domain Adaptation","authors":"Yiju Yang, Taejoon Kim, Guanghui Wang","doi":"10.1109/CRV55824.2022.00014","DOIUrl":"https://doi.org/10.1109/CRV55824.2022.00014","url":null,"abstract":"Adversarial training based on the maximum clas-sifier discrepancy between two classifier structures has achieved great success in unsupervised domain adaptation tasks for image classification. The approach adopts the structure of two classifiers, though simple and intuitive, the learned classification boundary may not well represent the data property in the new domain. In this paper, we propose to extend the structure to multiple classifiers to further boost its performance. To this end, we develop a very straightforward approach to adding more classifiers. We employ the principle that the classifiers are different from each other to construct a discrepancy loss function for multiple classifiers. The proposed construction method of loss function makes it possible to add any number of classifiers to the original framework. The proposed approach is validated through extensive experimental evaluations. We demonstrate that, on average, adopting the structure of three classifiers normally yields the best performance as a trade-off between accuracy and efficiency. With minimum extra computational costs, the proposed approach can significantly improve the performance of the original algorithm. The source code of the proposed approach can be downloaded from https://github.com/rucv/MMCD_DA.","PeriodicalId":131142,"journal":{"name":"2022 19th Conference on Robots and Vision (CRV)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125412295","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

The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation 半监督分割迭代自训练的GIST和RIST

2022 19th Conference on Robots and Vision (CRV) Pub Date : 2021-03-31 DOI: 10.1109/CRV55824.2022.00016

Eu Wern Teh, Terrance Devries, Brendan Duke, R. Jiang, P. Aarabi, Graham W. Taylor

引用次数: 2

首页上一页