2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP)最新文献_第6页

A Dual Path Deep Network for Single Image Super-Resolution Reconstruction 单幅图像超分辨率重建的双路径深度网络

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2018-08-01 DOI: 10.1109/MMSP.2018.8547049

Fateme S. Mirshahi, Parvaneh Saeedi

引用次数: 0

Adversarial Attacks on Face Detectors Using Neural Net Based Constrained Optimization 基于约束优化的神经网络人脸检测器对抗性攻击

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2018-05-31 DOI: 10.1109/MMSP.2018.8547128

A. Bose, P. Aarabi

{"title":"Adversarial Attacks on Face Detectors Using Neural Net Based Constrained Optimization","authors":"A. Bose, P. Aarabi","doi":"10.1109/MMSP.2018.8547128","DOIUrl":"https://doi.org/10.1109/MMSP.2018.8547128","url":null,"abstract":"Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image classification models, object detection pipelines have been much harder to break. In this paper, we propose a novel strategy to craft adversarial examples by solving a constrained optimization problem using an adversarial generator network. Our approach is fast and scalable, requiring only a forward pass through our trained generator network to craft an adversarial sample. Unlike in many attack strategies we show that the same trained generator is capable of attacking new images without explicitly optimizing on them. We evaluate our attack on a trained Faster R-CNN face detector on the cropped 300-W face dataset where we manage to reduce the number of detected faces to 0.5% of all originally detected faces. In a different experiment, also on 300-W, we demonstrate the robustness of our attack to a JPEG compression based defense typical JPEG compression level of 75% reduces the effectiveness of our attack from only 0.5% of detected faces to a modest 5.0%.","PeriodicalId":137522,"journal":{"name":"2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116362592","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: 79

MV-YOLO: Motion Vector-Aided Tracking by Semantic Object Detection 基于语义目标检测的运动矢量辅助跟踪

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2018-04-30 DOI: 10.1109/MMSP.2018.8547125

Saeed Ranjbar Alvar, I. Bajić

引用次数: 23

Near-Lossless Deep Feature Compression for Collaborative Intelligence 面向协同智能的近无损深度特征压缩

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2018-04-26 DOI: 10.1109/MMSP.2018.8547134

Hyomin Choi, I. Bajić

引用次数: 53

Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels 基于网格化超像素的高效内存深度显著目标分割网络

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2017-12-27 DOI: 10.1109/MMSP.2018.8547096

Çağlar Aytekin, Xingyang Ni, Francesco Cricri, Lixin Fan, Emre B. Aksu

{"title":"Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels","authors":"Çağlar Aytekin, Xingyang Ni, Francesco Cricri, Lixin Fan, Emre B. Aksu","doi":"10.1109/MMSP.2018.8547096","DOIUrl":"https://doi.org/10.1109/MMSP.2018.8547096","url":null,"abstract":"Computer vision algorithms with pixel-wise labeling tasks, such as semantic segmentation and salient object detection, have gone through a significant accuracy increase with the incorporation of deep learning. Deep segmentation methods slightly modify and fine-tune pre-trained networks that have hundreds of millions of parameters. In this work, we question the need of having such memory demanding networks for a reasonable performance in salient object segmentation. To this end, we propose a way to learn a memory-efficient network from scratch by training it only on salient object detection datasets. Our method encodes images to gridized superpixels that preserve both the object boundaries and the connectivity rules of regular pixels. This representation allows us to use convolutional neural networks that operate on regular grids. By using these encoded images, we train a memory-efficient network using only 0.048% of the number of parameters that a majority of other deep salient object detection networks have. Our method shows comparable accuracy with the state-of-the-art deep salient object detection methods and provides a much more memory-efficient alternative to them. Due to its easy deployment and small size, such a network is preferable for applications in memory limited IoT devices.","PeriodicalId":137522,"journal":{"name":"2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132651871","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: 2

A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement 基于DSP/深度学习的实时全频带语音增强方法

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2017-09-24 DOI: 10.1109/MMSP.2018.8547084

J. Valin

引用次数: 139