Data sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to the inherently high dimension of parameters in learning the sampling schedule. In this paper, we propose an AutoSampling method to automatically learn sampling schedules for model training, which consists of the multi-exploitation step aiming for optimal local sampling schedules and the exploration step for the ideal sampling distribution. More specifically, we achieve sampling schedule search with shortened exploitation cycle to provide enough supervision. In addition, we periodically estimate the sampling distribution from the learned sampling schedules and perturb it to search in the distribution space. The combination of two searches allows us to learn a robust sampling schedule. We apply our AutoSampling method to a variety of image classification tasks illustrating the effectiveness of the proposed method.
In large studies involving multi protocol Magnetic Resonance Imaging (MRI), it can occur to miss one or more sub-modalities for a given patient owing to poor quality (e.g. imaging artifacts), failed acquisitions, or hallway interrupted imaging examinations. In some cases, certain protocols are unavailable due to limited scan time or to retrospectively harmonise the imaging protocols of two independent studies. Missing image modalities pose a challenge to segmentation frameworks as complementary information contributed by the missing scans is then lost. In this paper, we propose a novel model, Multi-modal Gaussian Process Prior Variational Autoencoder (MGP-VAE), to impute one or more missing sub-modalities for a patient scan. MGP-VAE can leverage the Gaussian Process (GP) prior on the Variational Autoencoder (VAE) to utilize the subjects/patients and sub-modalities correlations. Instead of designing one network for each possible subset of present sub-modalities or using frameworks to mix feature maps, missing data can be generated from a single model based on all the available samples. We show the applicability of MGP-VAE on brain tumor segmentation where either, two, or three of four sub-modalities may be missing. Our experiments against competitive segmentation baselines with missing sub-modality on BraTS'19 dataset indicate the effectiveness of the MGP-VAE model for segmentation tasks.
This paper introduces a visual-based localization method for autonomous vehicles (AVs) that operate in the absence of any complicated hardware system but a single camera. Visual localization refers to techniques that aim to find the location of an object based on visual information of its surrounding area. The problem of localization has been of interest for many years. However, visual localization is a relatively new subject in the literature of transportation. Moreover, the inevitable application of this type of localization in the context of autonomous vehicles demands special attention from the transportation community to this problem. This study proposes a two-step localization method that requires a database of geotagged images and a camera mounted on a vehicle that can take pictures while the car is moving. The first step which is image retrieval uses SIFT local feature descriptor to find an initial location for the vehicle using image matching. The next step is to utilize the Kalman filter to estimate a more accurate location for the vehicle as it is moving. All stages of the introduced method are implemented as a complete system using different Python libraries. The proposed system is tested on the KITTI dataset and has shown an average accuracy of 2 meters in finding the final location of the vehicle.
Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x,y (and also z in 3D images) dimensions. However often only labels of the whole images are annotated, and localized ROIs are unavailable; and 3) ROIs in medical images often appear in varying sizes (scales). We approach these three challenges with a Multi-Instance Multi-Scale (MIMS) CNN: 1) We propose a multi-scale convolutional layer, which extracts patterns of different receptive fields with a shared set of convolutional kernels, so that scale-invariant patterns are captured by this compact set of kernels. As this layer contains only a small number of parameters, training on small datasets becomes feasible; 2) We propose a "top-k pooling"" to aggregate the feature maps in varying scales from multiple spatial dimensions, allowing the model to be trained using weak annotations within the multiple instance learning (MIL) framework. Our method is shown to perform well on three classification tasks involving two 3D and two 2D medical image datasets.
Diabetic Retinopathy (DR) is a leading cause of vision loss in the world,. In the past few Diabetic Retinopathy (DR) is a leading cause of vision loss in the world. In the past few years, Artificial Intelligence (AI) based approaches have been used to detect and grade DR. Early detection enables appropriate treatment and thus prevents vision loss, Both fundus and optical coherence tomography (OCT) images are used to image the retina. With deep learning/machine learning apprroaches it is possible to extract features from the images and detect the presence of DR. Multiple strategies are implemented to detect and grade the presence of DR using classification, segmentation, and hybrid techniques. This review covers the literature dealing with AI approaches to DR that have been published in the open literature over a five year span (2016-2021). In addition a comprehensive list of available DR datasets is reported. Both the PICO (P-patient, I-intervention, C-control O-outcome) and Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA)2009 search strategies were employed. We summarize a total of 114 published articles which conformed to the scope of the review. In addition a list of 43 major datasets is presented.
Under various poses and heavy occlusions,3D hand model reconstruction based on a single monocular RGB image has been a challenging problem in computer vision field for many years. In this paper, we propose a SR-Affine approach for high-quality 3D hand model reconstruction. First, we propose an encoder-decoder network architecture (AffineNet) for MANO hand reconstruction. Since MANO hand is not detailed, we further propose SRNet to up-sampling point-clouds by image super-resolution on the UV map. Many experiments demonstrate that our approach is robust and outperforms the state-of-the-art methods on standard benchmarks, including the FreiHAND and HO3D datasets.
The vulnerability of deep neural networks (DNNs) for adversarial examples have attracted more attention. Many algorithms are proposed to craft powerful adversarial examples. However, these algorithms modifying the global or local region of pixels without taking into account network explanations. Hence, the perturbations are redundancy and easily detected by human eyes. In this paper, we propose a novel method to generate local region perturbations. The main idea is to find the contributing feature regions (CFRs) of images based on network explanations for perturbations. Due to the network explanations, the perturbations added to the CFRs are more effective than other regions. In our method, a soft mask matrix is designed to represent the CFRs for finely characterizing the contributions of each pixel. Based on this soft mask, we develop a new objective function with inverse temperature to search for optimal perturbations in CFRs. Extensive experiments are conducted on CIFAR-10 and ILSVRC2012, which demonstrate the effectiveness, including attack success rate, imperceptibility,and transferability.
We can only allow human-robot-cooperation in a common work cell if the human integrity is guaranteed. A surveillance system with multiple cameras can detect collisions without contact to the human collaborator. A failure safe system needs to optimally cover the important areas of the robot work cell with safety overlap. We propose an efficient algorithm for optimally placing and orienting the cameras in a 3D CAD model of the work cell. In order to evaluate the quality of the camera constellation in each step, our method simulates the vision system using a z-buffer rendering technique for image acquisition, a voxel space for the overlap and a refined visual hull method for a conservative human reconstruction. The simulation allows to evaluate the quality with respect to the distortion of images and advanced image analysis in the presence of static and dynamic visual obstacles such as tables, racks, walls, robots and people. Our method is ideally suited for maximizing the coverage of multiple cameras or minimizing an error made by the visual hull and can be extended to probabilistic space carving.
Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes. For solving the task, an activity level measurement and a fusion rule are typically established to select and fuse the most relevant information from the sources. However, the design of this kind of method by hand is really hard and sometimes restricted to solution spaces where the optimal all-in-focus images are not contained. Then, we propose here two fast and straightforward approaches for image fusion based on deep neural networks. Our solution uses a multiple source Hourglass architecture trained in an end-to-end fashion. Models are data-driven and can be easily generalized for other kinds of fusion problems. A segmentation approach is used for recognition of the focus map, while the weighted average rule is used for fusion. We designed a training loss function for our regression-based fusion function, which allows the network to learn both the activity level measurement and the fusion rule. Experimental results show our approach has comparable results to the state-of-the-art methods with a 60X increase of computational efficiency for 520X520 resolution images.
In this paper, we present a novel differential morph detection framework, utilizing landmark and appearance disentanglement. In our framework, the face image is represented in the embedding domain using two disentangled but complementary representations. The network is trained by triplets of face images, in which the intermediate image inherits the landmarks from one image and the appearance from the other image. This initially trained network is further trained for each dataset using contrastive representations. We demonstrate that, by employing appearance and landmark disentanglement, the proposed framework can provide state-of-the-art differential morph detection performance. This functionality is achieved by the using distances in landmark, appearance, and ID domains. The performance of the proposed framework is evaluated using three morph datasets generated with different methodologies.