Low-dose Computed Tomography is a common issue in reality. Current reduction, sparse sampling and limited-view scanning can all cause it. Between them, limited-view CT is general in the industry due to inevitable mechanical and physical limitation. However, limited-view CT can cause serious imaging problem on account of its massive information loss. Thus, we should effectively utilize the scant prior information to perform completion. It is an undeniable fact that CT imaging slices are extremely dense, which leads to high continuity between successive images. We realized that fully exploit the spatial correlation between consecutive frames can significantly improve restoration results in video inpainting. Inspired by this, we propose a deep learning-based three-stage algorithm that hoist limited-view CT imaging quality based on spatial information. In stage one, to better utilize prior information in the Radon domain, we design an adversarial autoencoder to complement the Radon data. In the second stage, a model is built to perform inpainting based on spatial continuity in the image domain. At this point, we have roughly restored the imaging, while its texture still needs to be finely repaired. Hence, we propose a model to accurately restore the image in stage three, and finally achieve an ideal inpainting result. In addition, we adopt FBP instead of SART-TV to make our algorithm more suitable for real-time use. In the experiment, we restore and reconstruct the Radon data that has been cut the rear one-third part, they achieve PSNR of 40.209, SSIM of 0.943, while precisely present the texture.
Despite deep learning (DL) success in classification problems, DL classifiers do not provide a sound mechanism to decide when to refrain from predicting. Recent works tried to control the overall prediction risk with classification with rejection options. However, existing works overlook the different significance of different classes. We introduce Set-classifier with Class-specific RIsk Bounds (SCRIB) to tackle this problem, assigning multiple labels to each example. Given the output of a black-box model on the validation set, SCRIB constructs a set-classifier that controls the class-specific prediction risks with a theoretical guarantee. The key idea is to reject when the set classifier returns more than one label. We validated SCRIB on several medical applications, including sleep staging on electroencephalogram (EEG) data, X-ray COVID image classification, and atrial fibrillation detection based on electrocardiogram (ECG) data. SCRIB obtained desirable class-specific risks, which are 35\%-88\% closer to the target risks than baseline methods.
Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning a useful representation requires diverse data, while effective exploration is only possible with coherent representations. Furthermore, we would like to learn representations that not only generalize across tasks but also accelerate downstream exploration for efficient task-specific training. To address these challenges we propose Proto-RL, a self-supervised framework that ties representation learning with exploration through prototypical representations. These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations. We pre-train these task-agnostic representations and prototypes on environments without downstream task information. This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.
The quota system in Brazil made it possible to include blind students in higher education. Teachers' lack of knowledge about the braille system can represent a barrier between them and students who use it for writing and reading. Computer-vision-based transcription solutions represent mechanisms for reducing understanding restrictions on this system. However, such tools face nuisances inherent to image processing systems, e.g., illumination, noise, and scale, harming the result. This paper presents an automated approach to mitigate transcription errors in braille texts for the Portuguese language. We propose a selection function, combined with dictionaries, that provides the best correspondence of words based on their braille representation. We validated our proposal on a dataset of synthetic images by submitting them to different noise levels and testing the proposal's robustness. Experimental results confirm the effectiveness of the solution compared to a standard approach. As a contribution of this paper, we expect to provide a method to support robust and adaptable solutions to real use conditions.
Use of Deep Learning (DL) in commercial applications such as image classification, sentiment analysis and speech recognition is increasing. When training DL models with large number of parameters and/or large datasets, cost and speed of training can become prohibitive. Distributed DL training solutions that split a training job into subtasks and execute them over multiple nodes can decrease training time. However, the cost of current solutions, built predominantly for cluster computing systems, can still be an issue. In contrast to cluster computing systems, Volunteer Computing (VC) systems can lower the cost of computing, but applications running on VC systems have to handle fault tolerance, variable network latency and heterogeneity of compute nodes, and the current solutions are not designed to do so. We design a distributed solution that can run DL training on a VC system by using a data parallel approach. We implement a novel asynchronous SGD scheme called VC-ASGD suited for VC systems. In contrast to traditional VC systems that lower cost by using untrustworthy volunteer devices, we lower cost by leveraging preemptible computing instances on commercial cloud platforms. By using preemptible instances that require applications to be fault tolerant, we lower cost by 70-90% and improve data security.
Low light conditions in aerial images adversely affect the performance of several vision based applications. There is a need for methods that can efficiently remove the low light attributes and assist in the performance of key vision tasks. In this work, we propose a new method that is capable of enhancing the low light image in a self-supervised fashion, and sequentially apply detection and segmentation tasks in an end-to-end manner. The proposed method occupies a very small overhead in terms of memory and computational power over the original algorithm and delivers superior results. Additionally, we propose the generation of a new low light aerial dataset using GANs, which can be used to evaluate vision based networks for similar adverse conditions.
The training of medical image analysis systems using machine learning approaches follows a common script: collect and annotate a large dataset, train the classifier on the training set, and test it on a hold-out test set. This process bears no direct resemblance with radiologist training, which is based on solving a series of tasks of increasing difficulty, where each task involves the use of significantly smaller datasets than those used in machine learning. In this paper, we propose a novel training approach inspired by how radiologists are trained. In particular, we explore the use of meta-training that models a classifier based on a series of tasks. Tasks are selected using teacher-student curriculum learning, where each task consists of simple classification problems containing small training sets. We hypothesize that our proposed meta-training approach can be used to pre-train medical image analysis models. This hypothesis is tested on the automatic breast screening classification from DCE-MRI trained with weakly labeled datasets. The classification performance achieved by our approach is shown to be the best in the field for that application, compared to state of art baseline approaches: DenseNet, multiple instance learning and multi-task learning.
We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence applications in AR or VR, a faithful reproduction of the appearance including novel viewpoints or head-poses is required. In contrast to state-of-the-art approaches that model the geometry and material properties explicitly, or are purely image-based, we introduce an implicit representation of the head based on scene representation networks. To handle the dynamics of the face, we combine our scene representation network with a low-dimensional morphable model which provides explicit control over pose and expressions. We use volumetric rendering to generate images from this hybrid representation and demonstrate that such a dynamic neural scene representation can be learned from monocular input data only, without the need of a specialized capture setup. In our experiments, we show that this learned volumetric representation allows for photo-realistic image generation that surpasses the quality of state-of-the-art video-based reenactment methods.
Image understanding relies heavily on accurate multi-label classification. In recent years deep learning (DL) algorithms have become very successful tools for multi-label classification of image objects. With these set of tools, various implementations of DL algorithms have been released for the public use in the form of application programming interfaces (API). In this study, we evaluate and compare 10 of the most prominent publicly available APIs in a best-of-breed challenge. The evaluation is performed on the Visual Genome labeling benchmark dataset using 12 well-recognized similarity metrics. In addition, for the first time in this kind of comparison, we use a semantic similarity metric to evaluate the semantic similarity performance of these APIs. In this evaluation, Microsoft's Computer Vision, TensorFlow, Imagga, and IBM's Visual Recognition showed better performance than the other APIs. Furthermore, the new semantic similarity metric allowed deeper insights for comparison.
Large-scale transformer-based pre-training has recently revolutionized vision-and-language (V+L) research. Models such as LXMERT, ViLBERT and UNITER have significantly lifted the state of the art over a wide range of V+L tasks. However, the large number of parameters in such models hinders their application in practice. In parallel, work on the lottery ticket hypothesis has shown that deep neural networks contain small matching subnetworks that can achieve on par or even better performance than the dense networks when trained in isolation. In this work, we perform the first empirical study to assess whether such trainable subnetworks also exist in pre-trained V+L models. We use UNITER, one of the best-performing V+L models, as the testbed, and consolidate 7 representative V+L tasks for experiments, including visual question answering, visual commonsense reasoning, visual entailment, referring expression comprehension, image-text retrieval, GQA, and NLVR$^2$. Through comprehensive analysis, we summarize our main findings as follows. ($i$) It is difficult to find subnetworks (i.e., the tickets) that strictly match the performance of the full UNITER model. However, it is encouraging to confirm that we can find "relaxed" winning tickets at 50%-70% sparsity that maintain 99% of the full accuracy. ($ii$) Subnetworks found by task-specific pruning transfer reasonably well to the other tasks, while those found on the pre-training tasks at 60%/70% sparsity transfer universally, matching 98%/96% of the full accuracy on average over all the tasks. ($iii$) Adversarial training can be further used to enhance the performance of the found lottery tickets.