Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.
In this paper we present the first model for directly synthesizing fluent, natural-sounding spoken audio captions for images that does not require natural language text as an intermediate representation or source of supervision. Instead, we connect the image captioning module and the speech synthesis module with a set of discrete, sub-word speech units that are discovered with a self-supervised visual grounding task. We conduct experiments on the Flickr8k spoken caption dataset in addition to a novel corpus of spoken audio captions collected for the popular MSCOCO dataset, demonstrating that our generated captions also capture diverse visual semantics of the images they describe. We investigate several different intermediate speech representations, and empirically find that the representation must satisfy several important properties to serve as drop-in replacements for text.
Successful applications of deep learning (DL) requires large amount of annotated data. This often restricts the benefits of employing DL to businesses and individuals with large budgets for data-collection and computation. Summarization offers a possible solution by creating much smaller representative datasets that can allow real-time deep learning and analysis of big data and thus democratize use of DL. In the proposed work, our aim is to explore a novel approach to task-specific image corpus summarization using semantic information and self-supervision. Our method uses a classification-based Wasserstein generative adversarial network (CLSWGAN) as a feature generating network. The model also leverages rotational invariance as self-supervision and classification on another task. All these objectives are added on a features from resnet34 to make it discriminative and robust. The model then generates a summary at inference time by using K-means clustering in the semantic embedding space. Thus, another main advantage of this model is that it does not need to be retrained each time to obtain summaries of different lengths which is an issue with current end-to-end models. We also test our model efficacy by means of rigorous experiments both qualitatively and quantitatively.
Class imbalance occurs in many real-world applications, including image classification, where the number of images in each class differs significantly. With imbalanced data, the generative adversarial networks (GANs) leans to majority class samples. The two recent methods, Balancing GAN (BAGAN) and improved BAGAN (BAGAN-GP), are proposed as an augmentation tool to handle this problem and restore the balance to the data. The former pre-trains the autoencoder weights in an unsupervised manner. However, it is unstable when the images from different categories have similar features. The latter is improved based on BAGAN by facilitating supervised autoencoder training, but the pre-training is biased towards the majority classes. In this work, we propose a novel Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks (CAPGAN) as an augmentation tool to generate realistic synthetic images. In particular, we utilize a conditional convolutional variational autoencoder with supervised and balanced pre-training for the GAN initialization and training with gradient penalty. Our proposed method presents a superior performance of other state-of-the-art methods on the highly imbalanced version of MNIST, Fashion-MNIST, CIFAR-10, and two medical imaging datasets. Our method can synthesize high-quality minority samples in terms of Fr\'echet inception distance, structural similarity index measure and perceptual quality.
Deep neural networks have a great potential to improve image denoising in low-dose computed tomography (LDCT). Popular ways to increase the network capacity include adding more layers or repeating a modularized clone model in a sequence. In such sequential architectures, the noisy input image and end output image are commonly used only once in the training model, which however limits the overall learning performance. In this paper, we propose a parallel-clone neural network method that utilizes a modularized network model and exploits the benefit of parallel input, parallel-output loss, and clone-toclone feature transfer. The proposed model keeps a similar or less number of unknown network weights as compared to conventional models but can accelerate the learning process significantly. The method was evaluated using the Mayo LDCT dataset and compared with existing deep learning models. The results show that the use of parallel input, parallel-output loss, and clone-to-clone feature transfer all can contribute to an accelerated convergence of deep learning and lead to improved image quality in testing. The parallel-clone network has been demonstrated promising for LDCT image denoising.
This paper presents a novel deep reinforcement learning-based system for 3D mapless navigation for Unmanned Aerial Vehicles (UAVs). Instead of using a image-based sensing approach, we propose a simple learning system that uses only a few sparse range data from a distance sensor to train a learning agent. We based our approaches on two state-of-art double critic Deep-RL models: Twin Delayed Deep Deterministic Policy Gradient (TD3) and Soft Actor-Critic (SAC). We show that our two approaches manage to outperform an approach based on the Deep Deterministic Policy Gradient (DDPG) technique and the BUG2 algorithm. Also, our new Deep-RL structure based on Recurrent Neural Networks (RNNs) outperforms the current structure used to perform mapless navigation of mobile robots. Overall, we conclude that Deep-RL approaches based on double critic with Recurrent Neural Networks (RNNs) are better suited to perform mapless navigation and obstacle avoidance of UAVs.
We present a novel, blind, single image deblurring method that utilizes information regarding blur kernels. Our model solves the deblurring problem by dividing it into two successive tasks: (1) blur kernel estimation and (2) sharp image restoration. We first introduce a kernel estimation network that produces adaptive blur kernels based on the analysis of the blurred image. The network learns the blur pattern of the input image and trains to generate the estimation of image-specific blur kernels. Subsequently, we propose a long-term residual blending network that restores sharp images using the estimated blur kernel. To use the kernel efficiently, we propose a blending block that encodes features from both blurred images and blur kernels into a low dimensional space and then decodes them simultaneously to obtain an appropriately synthesized feature representation. We evaluate our model on REDS, GOPRO and Flickr2K datasets using various Gaussian blur kernels. Experiments show that our model can achieve excellent results on each dataset.
In image denoising problems, the increasing density of available images makes an exhaustive visual inspection impossible and therefore automated methods based on machine-learning must be deployed for this purpose. This is particulary the case in seismic signal processing. Engineers/geophysicists have to deal with millions of seismic time series. Finding the sub-surface properties useful for the oil industry may take up to a year and is very costly in terms of computing/human resources. In particular, the data must go through different steps of noise attenuation. Each denoise step is then ideally followed by a quality control (QC) stage performed by means of human expertise. To learn a quality control classifier in a supervised manner, labeled training data must be available, but collecting the labels from human experts is extremely time-consuming. We therefore propose a novel active learning methodology to sequentially select the most relevant data, which are then given back to a human expert for labeling. Beyond the application in geophysics, the technique we promote in this paper, based on estimates of the local error and its uncertainty, is generic. Its performance is supported by strong empirical evidence, as illustrated by the numerical experiments presented in this article, where it is compared to alternative active learning strategies both on synthetic and real seismic datasets.
Since the onset of the COVID-19 pandemic in 2020, millions of people have succumbed to this deadly virus. Many attempts have been made to devise an automated method of testing that could detect the virus. Various researchers around the globe have proposed deep learning based methodologies to detect the COVID-19 using Chest X-Rays. However, questions have been raised on the presence of bias in the publicly available Chest X-Ray datasets which have been used by the majority of the researchers. In this paper, we propose a 2 staged methodology to address this topical issue. Two experiments have been conducted as a part of stage 1 of the methodology to exhibit the presence of bias in the datasets. Subsequently, an image segmentation, super-resolution and CNN based pipeline along with different image augmentation techniques have been proposed in stage 2 of the methodology to reduce the effect of bias. InceptionResNetV2 trained on Chest X-Ray images that were augmented with Histogram Equalization followed by Gamma Correction when passed through the pipeline proposed in stage 2, yielded a top accuracy of 90.47% for 3-class (Normal, Pneumonia, and COVID-19) classification task.
During the training for snowboard big air, one of the most popular winter sports, athletes and coaches extensively shoot and check their jump attempts using a single camera or smartphone. However, by watching videos sequentially, it is difficult to compare the precise difference in performance between two trials. Therefore, side-by-side display or overlay of two videos may be helpful for training. To accomplish this, the spatial and temporal alignment of multiple performances must be ensured. In this study, we propose a conventional but plausible solution using the existing image processing techniques for snowboard big air training. We conducted interviews with expert snowboarders who stated that the spatiotemporally aligned videos enabled them to precisely identify slight differences in body movements. The results suggest that the proposed method can be used during the training of snowboard big air.