Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Hao Ji

Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

Sep 10, 2019
Eitan Rothberg, Tingting Chen, Luo Jie, Hao Ji

Figure 1 for Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

Figure 2 for Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

Figure 3 for Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

Figure 4 for Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the backgrounds of normal images. We first use this attack to highlight the unnecessary sensitivity of neural networks to changes in the background of an image, then use it as part of a new training technique: localized adversarial training. By including locally adversarial images in the training set, we are able to create a classifier that suffers less loss than a non-adversarially trained counterpart model on both natural and adversarial inputs. The evaluation of our localized adversarial training algorithm on MNIST and CIFAR-10 datasets shows decreased accuracy loss on natural images, and increased robustness against adversarial inputs.

* 4 pages (excluding references). Presented at AdvML: 1st Workshop on Adversarial Learning Methods for Machine Learning and Data Mining at KDD '19

Via

Access Paper or Ask Questions

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Dec 15, 2016
Bin Liu, Hao Ji, Yi Dai

Figure 1 for Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Figure 2 for Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Figure 3 for Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Figure 4 for Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

In this paper, we describe work in progress towards a real-time vision-based traffic flow prediction (TFP) system. The proposed method consists of three elemental operators, that are dynamic texture model based motion segmentation, feature extraction and Gaussian process (GP) regression. The objective of motion segmentation is to recognize the target regions covering the moving vehicles in the sequence of visual processes. The feature extraction operator aims to extract useful features from the target regions. The extracted features are then mapped to the number of vehicles through the operator of GP regression. A training stage using historical visual data is required for determining the parameter values of the GP. Using a low-resolution visual data set, we performed preliminary evaluations on the performance of the proposed method. The results show that our method beats a benchmark solution based on Gaussian mixture model, and has the potential to be developed into qualified and practical solutions to real-time TFP.

* 8 pages, 4 figures, conference

Via

Access Paper or Ask Questions