相关论文: Cyclone intensity estimate with context-aware cycl…

Many current methods to interpret convolutional neural networks (CNNs) use visualization techniques and words to highlight concepts of the input seemingly relevant to a CNN's decision. The methods hypothesize that the recognition of these…

Intensifying climate change will lead to more extreme weather events, including heavy rainfall and drought. Accurate stream flow prediction models which are adaptable and robust to new circumstances in a changing climate will be an…

The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other…

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly…

Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, and flow-based models. GANs have dramatically improved sample…

Deep learning-based approaches achieve state-of-the-art performance in the majority of image segmentation benchmarks. However, training of such models requires a sizable amount of manual annotations. In order to reduce this effort, we…

The literature shows outstanding capabilities for CNNs in event recognition in images. However, fewer attempts are made to analyze the potential causes behind the decisions of the models and exploring whether the predictions are based on…

Climate hazards can cause major disasters when they occur simultaneously as compound hazards. To understand the distribution of climate risk and inform adaptation policies, scientists need to simulate a large number of physically realistic…

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to…

Lane segmentation is a challenging issue in autonomous driving system designing because lane marks show weak textural consistency due to occlusion or extreme illumination but strong geometric continuity in traffic images, from which general…

CycleGAN provides a framework to train image-to-image translation with unpaired datasets using cycle consistency loss [4]. While results are great in many applications, the pixel level cycle consistency can potentially be problematic and…

Deep learning techniques have become prominent in modern fault diagnosis for complex processes. In particular, convolutional neural networks (CNNs) have shown an appealing capacity to deal with multivariate time-series data by converting…

Classification using supervised learning requires annotating a large amount of classes-balanced data for model training and testing. This has practically limited the scope of applications with supervised learning, in particular deep…

Understanding the mechanism of generative adversarial networks (GANs) helps us better use GANs for downstream applications. Existing efforts mainly target interpreting unconditional models, leaving it less explored how a conditional GAN…

The deep learning technique has been applied for the first time to investigate the possibility of centrality determination in terms of the number of participants ($N_{\mathrm{part}}$) in high-energy heavy-ion collisions. For this purpose,…

Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level…

Heavy precipitation from tropical cyclones (TCs) may result in disasters, such as floods and landslides, leading to substantial economic damage and loss of life. Prediction of TC precipitation based on ensemble post-processing procedures…

We address the challenging problem of deep representation learning--the efficient adaption of a pre-trained deep network to different tasks. Specifically, we propose to explore gradient-based features. These features are gradients of the…

Many previous methods have showed the importance of considering semantically relevant objects for performing event recognition, yet none of the methods have exploited the power of deep convolutional neural networks to directly integrate…

Capturing long-range dependencies in feature representations is crucial for many visual recognition tasks. Despite recent successes of deep convolutional networks, it remains challenging to model non-local context relations between visual…