In this paper, we propose Perceptual Adversarial Networks (PAN) for image-to-image transformations. Different from existing application driven algorithms, PAN provides a generic framework of learning to map from input images to desired images (Fig. 1), such as a rainy image to its de-rained counterpart, object edges to photos, semantic labels to a scenes image, etc. The proposed PAN consists of two feed-forward convolutional neural networks (CNNs): the image transformation network T and the discriminative network D. Besides the generative adversarial loss widely used in GANs, we propose the perceptual adversarial loss, which undergoes an adversarial training process between the image transformation network T and the hidden layers of the discriminative network D. The hidden layers and the output of the discriminative network D are upgraded to constantly and automatically discover the discrepancy between the transformed image and the corresponding ground-truth, while the image transformation network T is trained to minimize the discrepancy explored by the discriminative network D. Through integrating the generative adversarial loss and the perceptual adversarial loss, D and T can be trained alternately to solve image-to-image transformation tasks. Experiments evaluated on several image-to-image transformation tasks (e.g., image de-raining, image inpainting, etc) demonstrate the effectiveness of the proposed PAN and its advantages over many existing works.

Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this paper, we propose a novel GAN framework called evolutionary generative adversarial networks (E-GAN) for stable GAN training and improved generative performance. Unlike existing GANs, which employ a pre-defined adversarial objective function alternately training a generator and a discriminator, we utilize different adversarial training objectives as mutation operations and evolve a population of generators to adapt to the environment (i.e., the discriminator). We also utilize an evaluation mechanism to measure the quality and diversity of generated samples, such that only well-performing generator(s) are preserved and used for further training. In this way, E-GAN overcomes the limitations of an individual adversarial training objective and always preserves the best offspring, contributing to progress in and the success of GANs. Experiments on several datasets demonstrate that E-GAN achieves convincing generative performance and reduces the training problems inherent in existing GANs.

In the past few years, intelligent structural damage identification algorithms based on machine learning techniques have been developed and obtained considerable attentions worldwide, due to the advantages of reliable analysis and high efficiency. However, the performances of existing machine learning–based damage identification methods are heavily dependent on the selected signatures from raw signals. This will cause the fact that the damage identification method, which is the optimal solution for a specific application, may fail to provide the similar performance on other cases. Besides, the feature extraction is a time-consuming task, which may affect the real-time performance in practical applications. To address these problems, this article proposes a novel method based on deep convolutional neural networks to identify and localise damages of building structures equipped with smart control devices. The proposed deep convolutional neural network is capable of automatically extracting high-level features from raw signals or low-level features and optimally selecting the combination of extracted features via a multi-layer fusion to satisfy any damage identification objective. To evaluate the performance of the proposed deep convolutional neural network method, a five-level benchmark building equipped with adaptive smart isolators subjected to the seismic loading is investigated. The result shows that the proposed method has outstanding generalisation capacity and higher identification accuracy than other commonly used machine learning methods. Accordingly, it is deemed as an ideal and effective method for damage identification of smart structures.

No abstract

No abstract