Search

Artificial intelligence is developing rapidly in the direction of intellectualization and humanization. Recent studies have shown the vulnerability of many deep learning models to adversarial examples, but there are fewer studies on adversarial examples attacking facial expression recognition systems. Human–computer interaction requires facial expression recognition, so the security demands of artificial intelligence humanization should be considered. Inspired by facial expression recognition, we want to explore the characteristics of facial expression recognition adversarial examples. In this paper, we are the first to study facial expression adversarial examples (FEAEs) and propose an adversarial attack method on facial expression recognition systems, a novel measurement method on the adversarial hardness of FEAEs, and two evaluation metrics on FEAE transferability. The experimental results illustrate that our approach is superior to other gradient-based attack methods. Finding FEAEs can attack not only facial expression recognition systems but also face recognition systems. The transferability and adversarial hardness of FEAEs can be measured effectively and accurately. [ABSTRACT FROM AUTHOR]

Although the policy-gradient methods for reinforcement learning have shown significant improvement in image captioning, how to achieve high performance during the reinforcement optimizing process is still not a simple task. There are at least two difficulties: (1) The large size of vocabulary leads to a large action space, which makes it difficult for the model to accurately predict the current word. (2) The large variance of gradient estimation in reinforcement learning usually causes severe instabilities in the training process. In this paper, we propose two innovations to boost the performance of self-critical sequence training (SCST). First, we modify the standard long short-term memory (LSTM)based decoder by introducing a gate function to reduce the search scope of the vocabulary for any given image, which is termed the word gate decoder. Second, instead of only considering current maximum actions greedily, we propose a stabilized gradient estimation method whose gradient variance is controlled by the difference between the sampling reward from the current model and the expectation of the historical reward. We conducted extensive experiments, and results showed that our method could accelerate the training process and increase the prediction accuracy. Our method was validated on MS COCO datasets and yielded state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Image captioning is a challenging task. Meanwhile, it is important for the machine to understand the meaning of an image better. In recent years, the image captioning usually use the long-short-term-memory (LSTM) as the decoder to generate the sentence, and these models show excellent performance. Although the LSTM can memorize dependencies, the LSTM structure has complicated and inherently sequential across time problems. To address these issues, recent works have shown benefits of the Transformer for machine translation. Inspired by their success, we develop a Captioning Transformer (CT) model with stacked attention modules. We attempt to introduce the Transformer to the image captioning task. The CT model contains only attention modules without the dependencies of the time. It not only can memorize dependencies between the sequence but also can be trained in parallel. Moreover, we propose the multi-level supervision to make the Transformer achieve better performance. Extensive experiments are carried out on the challenging MSCOCO dataset and the proposed Captioning Transformer achieves competitive performance compared with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract Image captioning aims to describe the content of images with a sentence. It is a natural way for people to express their understanding, but a challenging and important task from the view of image understanding. In this paper, we propose two innovations to improve the performance of such a sequence learning problem. First, we give a new attention method named triple attention (TA-LSTM) which can leverage the image context information at every stage of LSTM. Then, we redesign the structure of basic LSTM, in which not only the stacked LSTM but also the paralleled LSTM are adopted, called as PS-LSTM. In this structure, we not only use the stack LSTM but also use the parallel LSTM to achieve the improvement of the performance compared with the normal LSTM. Through this structure, the proposed model can ensemble more parameters on single model and has ensemble ability itself. Through numerical experiments, on the public available MSCOCO dataset, our final TA-PS-LSTM model achieves comparable performance with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

• A novel method that facial expression saliency maps are proposed to generate facial expression adversarial examples. • The OMIM is proposed to help facial expression saliency maps accelerate to generate facial expression adversarial examples. • Our method is superior to other attack methods, such as FGSM, PGD, BIM, CW. The security demands in humanization should be considered as important, because artificial intelligence is developing rapidly in this area. Recent studies have shown the vulnerability of many deep learning models to adversarial examples; however, only a few studies on facial expression adversarial examples have been conducted. Thus, in this paper, we propose a novel method for generating facial expression adversarial examples using facial saliency maps and facial masking maps. Extensive numerical experiments demonstrate the outstanding performance of our method in terms of attack accuracy, structural similarity index measure score, and computational time, compared with other leading methods, such as the fast gradient sign method, projected gradient descent method, and Carlini–Wagner attacks. [ABSTRACT FROM AUTHOR]