Lijian Lin, Haosheng Chen, Yanjie Liang, Y. Yan, Hanzi Wang
{"title":"基于统计正样本生成和梯度感知学习的鲁棒视觉跟踪","authors":"Lijian Lin, Haosheng Chen, Yanjie Liang, Y. Yan, Hanzi Wang","doi":"10.1145/3338533.3366556","DOIUrl":null,"url":null,"abstract":"In recent years, Convolutional Neural Network (CNN) based trackers have achieved state-of-the-art performance on multiple benchmark datasets. Most of these trackers train a binary classifier to distinguish the target from its background. However, they suffer from two limitations. Firstly, these trackers cannot effectively handle significant appearance variations due to the limited number of positive samples. Secondly, there exists a significant imbalance of gradient contributions between easy and hard samples, where the easy samples usually dominate the computation of gradient. In this paper, we propose a robust tracking method via Statistical Positive sample generation and Gradient Aware learning (SPGA) to address the above two limitations. To enrich the diversity of positive samples, we present an effective and efficient statistical positive sample generation algorithm to generate positive samples in the feature space. Furthermore, to handle the issue of imbalance between easy and hard samples, we propose a gradient sensitive loss to harmonize the gradient contributions between easy and hard samples. Extensive experiments on three challenging benchmark datasets including OTB50, OTB100 and VOT2016 demonstrate that the proposed SPGA performs favorably against several state-of-the-art trackers.","PeriodicalId":273086,"journal":{"name":"Proceedings of the ACM Multimedia Asia","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning\",\"authors\":\"Lijian Lin, Haosheng Chen, Yanjie Liang, Y. Yan, Hanzi Wang\",\"doi\":\"10.1145/3338533.3366556\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, Convolutional Neural Network (CNN) based trackers have achieved state-of-the-art performance on multiple benchmark datasets. Most of these trackers train a binary classifier to distinguish the target from its background. However, they suffer from two limitations. Firstly, these trackers cannot effectively handle significant appearance variations due to the limited number of positive samples. Secondly, there exists a significant imbalance of gradient contributions between easy and hard samples, where the easy samples usually dominate the computation of gradient. In this paper, we propose a robust tracking method via Statistical Positive sample generation and Gradient Aware learning (SPGA) to address the above two limitations. To enrich the diversity of positive samples, we present an effective and efficient statistical positive sample generation algorithm to generate positive samples in the feature space. Furthermore, to handle the issue of imbalance between easy and hard samples, we propose a gradient sensitive loss to harmonize the gradient contributions between easy and hard samples. Extensive experiments on three challenging benchmark datasets including OTB50, OTB100 and VOT2016 demonstrate that the proposed SPGA performs favorably against several state-of-the-art trackers.\",\"PeriodicalId\":273086,\"journal\":{\"name\":\"Proceedings of the ACM Multimedia Asia\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-12-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ACM Multimedia Asia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3338533.3366556\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ACM Multimedia Asia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3338533.3366556","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning
In recent years, Convolutional Neural Network (CNN) based trackers have achieved state-of-the-art performance on multiple benchmark datasets. Most of these trackers train a binary classifier to distinguish the target from its background. However, they suffer from two limitations. Firstly, these trackers cannot effectively handle significant appearance variations due to the limited number of positive samples. Secondly, there exists a significant imbalance of gradient contributions between easy and hard samples, where the easy samples usually dominate the computation of gradient. In this paper, we propose a robust tracking method via Statistical Positive sample generation and Gradient Aware learning (SPGA) to address the above two limitations. To enrich the diversity of positive samples, we present an effective and efficient statistical positive sample generation algorithm to generate positive samples in the feature space. Furthermore, to handle the issue of imbalance between easy and hard samples, we propose a gradient sensitive loss to harmonize the gradient contributions between easy and hard samples. Extensive experiments on three challenging benchmark datasets including OTB50, OTB100 and VOT2016 demonstrate that the proposed SPGA performs favorably against several state-of-the-art trackers.