2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)最新文献

筛选

英文中文

Domain Adaptive Knowledge Distillation for Driving Scene Semantic Segmentation 基于领域自适应知识蒸馏的驾驶场景语义分割

2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW) Pub Date : 2020-11-03 DOI: 10.1109/WACVW52041.2021.00019

D. Kothandaraman, Athira M. Nambiar, Anurag Mittal

{"title":"Domain Adaptive Knowledge Distillation for Driving Scene Semantic Segmentation","authors":"D. Kothandaraman, Athira M. Nambiar, Anurag Mittal","doi":"10.1109/WACVW52041.2021.00019","DOIUrl":"https://doi.org/10.1109/WACVW52041.2021.00019","url":null,"abstract":"Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the model with the ability to deal with these issues in a comprehensive manner. We term this as “Domain Adaptive Knowledge Distillation ” and address the same in the context of unsupervised domain-adaptive semantic segmentation by proposing a multi-level distillation strategy to effectively distil knowledge at different levels. Further, we introduce a novel cross entropy loss that leverages pseudo labels from the teacher. These pseudo teacher labels play a multifaceted role towards: (i) knowledge distillation from the teacher network to the student network & (ii) serving as a proxy for the ground truth for target domain images, where the problem is completely unsupervised. We introduce four paradigms for distilling domain adaptive knowledge and carry out extensive experiments and ablation studies on real-to-real as well as synthetic-to-real scenarios. Our experiments demonstrate the profound success of our proposed method.","PeriodicalId":313062,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114836047","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: 17

Per-frame mAP Prediction for Continuous Performance Monitoring of Object Detection During Deployment 部署过程中目标检测连续性能监控的逐帧mAP预测

2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW) Pub Date : 2020-09-18 DOI: 10.1109/WACVW52041.2021.00021

Q. Rahman, N. Sunderhauf, Feras Dayoub

引用次数: 10

Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack 使用约束优化的基于相似性攻击的可取消生物特征的可解释安全性分析

2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW) Pub Date : 2020-06-23 DOI: 10.1109/WACVW52041.2021.00012

Hanrui Wang, Xingbo Dong, Zhe Jin, A. Teoh, M. Tistarelli

{"title":"Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack","authors":"Hanrui Wang, Xingbo Dong, Zhe Jin, A. Teoh, M. Tistarelli","doi":"10.1109/WACVW52041.2021.00012","DOIUrl":"https://doi.org/10.1109/WACVW52041.2021.00012","url":null,"abstract":"In cancellable biometrics (CB) schemes, template security is achieved by applying, mainly non-linear, transformations to the biometric template. The transformation is designed to preserve the template distance/similarity in the transformed domain. Despite its effectiveness, the security issues attributed to similarity preservation property of CB are underestimated. Dong et al. [BTAS’19], exploited the similarity preservation trait of CB and proposed a similarity-based attack with high successful attack rate. The similarity-based attack utilizes preimage that are generated from the protected biometric template for impersonation and perform cross matching. In this paper, we propose a constrained optimization similarity-based attack (CSA), which is improved upon Dong’s genetic algorithm enabled similarity-based attack (GASA). The CSA applies algorithm-specific equality or inequality relations as constraints, to optimize preimage generation. We interpret the effectiveness of CSA from the supervised learning perspective. We identify such constraints then conduct extensive experiments to demonstrate CSA against CB with LFW face dataset. The results suggest that CSA is effective to breach IoM hashing and BioHashing security, and outperforms GASA significantly. Inferring from the above results, we further remark that, other than IoM and BioHashing, CSA is critical to other CB schemes as far as the constraints can be formulated. Furthermore, we reveal the correlation of hash code size and the attack performance of CSA.","PeriodicalId":313062,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133473796","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: 11

首页上一页