Improving adversarial robustness of deep neural networks by using semantic information

The recommendation method based on user sessions is mainly to model sessions as sequences in the assumption that user behaviors are independent and identically distributed, and then to use deep semantic information mining through Deep Neural Networks. Nevertheless, user behaviors may be a nonindependent intention at irregular points in time. For example, users may buy painkillers, books, or clothes for different reasons at different times. However, this has not been taken seriously in previous studies. Therefore, we propose a session recommendation method based on Neural Differential Equations in an attempt to predict user behavior forward or backward from any point in time. We used Ordinary Differential Equations to train the Graph Neural Network and could predict forward or backward at any point in time to model the user's nonindependent sessions. We tested for four real datasets and found that our model achieved the expected results and was superior to the existing session-based recommendations.

Download Full-text

Group-Wise Dynamic Dropout Based on Latent Semantic Variations

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6782 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11229-11236

Author(s):

Zhiwei Ke ◽

Zhiwei Wen ◽

Weicheng Xie ◽

Yi Wang ◽

Linlin Shen

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Semantic Information ◽

State Of The Art ◽

Classification Performance ◽

Network Robustness ◽

Feature Detectors ◽

Data Points ◽

Adversarial Examples ◽

Public Datasets

Dropout regularization has been widely used in various deep neural networks to combat overfitting. It works by training a network to be more robust on information-degraded data points for better generalization. Conventional dropout and variants are often applied to individual hidden units in a layer to break up co-adaptations of feature detectors. In this paper, we propose an adaptive dropout to reduce the co-adaptations in a group-wise manner by coarse semantic information to improve feature discriminability. In particular, we showed that adjusting the dropout probability based on local feature densities can not only improve the classification performance significantly but also enhance the network robustness against adversarial examples in some cases. The proposed approach was evaluated in comparison with the baseline and several state-of-the-art adaptive dropouts over four public datasets of Fashion-MNIST, CIFAR-10, CIFAR-100 and SVHN.

Download Full-text

CrowdTC: Crowd-powered Learning for Text Classification

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3457216 ◽

2021 ◽

Vol 16 (1) ◽

pp. 1-23

Author(s):

Keyu Yang ◽

Yunjun Gao ◽

Lei Liang ◽

Song Bian ◽

Lu Chen ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Text Classification ◽

Deep Neural Networks ◽

Semantic Information ◽

Human Beings ◽

Hybrid Neural Network ◽

Public Datasets ◽

Almost All ◽

The Cost

Text classification is a fundamental task in content analysis. Nowadays, deep learning has demonstrated promising performance in text classification compared with shallow models. However, almost all the existing models do not take advantage of the wisdom of human beings to help text classification. Human beings are more intelligent and capable than machine learning models in terms of understanding and capturing the implicit semantic information from text. In this article, we try to take guidance from human beings to classify text. We propose Crowd-powered learning for Text Classification (CrowdTC for short). We design and post the questions on a crowdsourcing platform to extract keywords in text. Sampling and clustering techniques are utilized to reduce the cost of crowdsourcing. Also, we present an attention-based neural network and a hybrid neural network to incorporate the extracted keywords as human guidance into deep neural networks. Extensive experiments on public datasets confirm that CrowdTC improves the text classification accuracy of neural networks by using the crowd-powered keyword guidance.

Download Full-text

SEMANTIC SEGMENTATION OF BUILDING IN AIRBORNE IMAGES

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w13-35-2019 ◽

2019 ◽

Vol XLII-2/W13 ◽

pp. 35-42 ◽

Cited By ~ 1

Author(s):

S. Huang ◽

F. Nex ◽

Y. Lin ◽

M. Y. Yang

Keyword(s):

Neural Networks ◽

Image Matching ◽

Urban Areas ◽

Deep Neural Networks ◽

Semantic Information ◽

Semantic Segmentation ◽

Point Clouds ◽

Dense Image ◽

2D And 3D ◽

Rgb Image

<p><strong>Abstract.</strong> Building is a key component to the reconstructing of LoD3 city modelling. Compared to terrestrial view, airborne datasets have more occlusions at street level but can cover larger area in the urban areas. With the popularity of the Deep Learning, many tasks in the field of computer vision can be solved in easier and efficiency way. In this paper, we propose a method to apply deep neural networks to building façade segmentation. In particular, the FC-DenseNet and the DeepLabV3+ algorithms are used to segment the building from airborne images and get semantic information such as, wall, roof, balcony and opening area. The patch-wise segmentation is used in the training and testing process in order to get information at pixel level. Different typologies of input have been considered: beside the conventional 2D information (i.e. RGB image), we combined 2D information with 3D features extracted from dense image matching point clouds to improve the performance of the segmentation. Results show that FC-DenseNet trained with 2D and 3D features achieves the best result, IoU up to 64.41%, it increases 5.13% compared to the result of the same model trained without 3D features.</p>

Download Full-text