Comput. Vis. Image Underst.最新文献_第7页

Learning language to symbol and language to vision mapping for visual grounding 学习语言以符号和语言以视觉映射为视觉基础

Comput. Vis. Image Underst. Pub Date : 2022-04-01 DOI: 10.2139/ssrn.3989572

Su He, Xiaofeng Yang, Guosheng Lin

引用次数: 1

MMSNet: Multi-modal scene recognition using multi-scale encoded features 使用多尺度编码特征的多模态场景识别

Comput. Vis. Image Underst. Pub Date : 2022-04-01 DOI: 10.2139/ssrn.4032570

Ali Caglayan, Nevrez Imamoglu, Ryosuke Nakamura

引用次数: 2

Periocular Biometrics and its Relevance to Partially Masked Faces: A Survey 眼周生物识别及其与部分蒙面的相关性:一项调查

Comput. Vis. Image Underst. Pub Date : 2022-03-29 DOI: 10.2139/ssrn.4029455

Renu Sharma, A. Ross

引用次数: 11

Meta conditional variational auto-encoder for domain generalization 面向领域泛化的元条件变分自编码器

Comput. Vis. Image Underst. Pub Date : 2022-01-01 DOI: 10.2139/ssrn.3988579

Zhiqiang Ge, Zhihuan Song, Xin Li, Lei Zhang

引用次数: 0

Handcrafted localized phase features for human action recognition 用于人类动作识别的手工局部相位特征

Comput. Vis. Image Underst. Pub Date : 2022-01-01 DOI: 10.2139/ssrn.4022915

S. Hejazi, G. Abhayaratne

引用次数: 7

Controlling strokes in fast neural style transfer using content transforms 使用内容变换控制快速神经风格传递中的笔画

Comput. Vis. Image Underst. Pub Date : 2022-01-01 DOI: 10.1007/s00371-022-02518-x

M. Reimann, Benito Buchheim, Amir Semmo, J. Döllner, Matthias Trapp

引用次数: 9

Conditional generative data-free knowledge distillation 条件生成无数据知识蒸馏

Comput. Vis. Image Underst. Pub Date : 2021-12-31 DOI: 10.2139/ssrn.4039886

Xinyi Yu, Ling Yan, Yang Yang, Libo Zhou, Linlin Ou

{"title":"Conditional generative data-free knowledge distillation","authors":"Xinyi Yu, Ling Yan, Yang Yang, Libo Zhou, Linlin Ou","doi":"10.2139/ssrn.4039886","DOIUrl":"https://doi.org/10.2139/ssrn.4039886","url":null,"abstract":"Knowledge distillation has made remarkable achievements in model compression. However, most existing methods require the original training data, which is usually unavailable due to privacy and security issues. In this paper, we propose a conditional generative data-free knowledge distillation (CGDD) framework for training lightweight networks without any training data. This method realizes efficient knowledge distillation based on conditional image generation. Specifically, we treat the preset labels as ground truth to train a conditional generator in a semi-supervised manner. The trained generator can produce specified classes of training images. For training the student network, we force it to extract the knowledge hidden in teacher feature maps, which provide crucial cues for the learning process. Moreover, an adversarial training framework for promoting distillation performance is constructed by designing several loss functions. This framework helps the student model to explore larger data space. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on different datasets. Compared with other data-free works, our work obtains state-of-the-art results on CIFAR100, Caltech101, and different versions of ImageNet datasets. The codes will be released.","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74094001","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

A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification 一种用于无监督域自适应再识别的伪标记实践的形式化方法

Comput. Vis. Image Underst. Pub Date : 2021-12-24 DOI: 10.2139/ssrn.3994206

Fabian Dubourvieux, Romaric Audigier, Angélique Loesch, Samia Ainouz, S. Canu

{"title":"A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification","authors":"Fabian Dubourvieux, Romaric Audigier, Angélique Loesch, Samia Ainouz, S. Canu","doi":"10.2139/ssrn.3994206","DOIUrl":"https://doi.org/10.2139/ssrn.3994206","url":null,"abstract":"The use of pseudo-labels prevails in order to tackle Unsupervised Domain Adaptive (UDA) Re-Identification (re-ID) with the best performance. Indeed, this family of approaches has given rise to several UDA re-ID specific frameworks, which are effective. In these works, research directions to improve Pseudo-Labeling UDA re-ID performance are varied and mostly based on intuition and experiments: refining pseudo-labels, reducing the impact of errors in pseudo-labels... It can be hard to deduce from them general good practices, which can be implemented in any Pseudo-Labeling method, to consistently improve its performance. To address this key question, a new theoretical view on Pseudo-Labeling UDA re-ID is proposed. The contributions are threefold: (i) A novel theoretical framework for Pseudo-Labeling UDA re-ID, formalized through a new general learning upper-bound on the UDA re-ID performance. (ii) General good practices for Pseudo-Labeling, directly deduced from the interpretation of the proposed theoretical framework, in order to improve the target re-ID performance. (iii) Extensive experiments on challenging person and vehicle cross-dataset re-ID tasks, showing consistent performance improvements for various state-of-the-art methods and various proposed implementations of good practices.","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79628369","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

A novel privacy-preserving outsourcing computation scheme for Canny edge detection 一种新的Canny边缘检测保密外包计算方案

Comput. Vis. Image Underst. Pub Date : 2021-10-30 DOI: 10.1007/s00371-021-02307-y

Bowen Li, Fazhi He, Xiantao Zeng

引用次数: 4

A Dynamic Keypoints Selection Network for 6DoF Pose Estimation 一种用于6自由度姿态估计的动态关键点选择网络

Comput. Vis. Image Underst. Pub Date : 2021-10-24 DOI: 10.1016/j.imavis.2022.104372

Haowen Sun, Taiyong Wang

引用次数: 5