Photorealistic style transfer is the task of transferring the artistic style of an image onto a content target, producing a result that is plausibly taken with a camera. Recent approaches, based on deep neural networks, produce impressive results but are either too slow to run at practical resolutions, or still contain objectionable artifacts. We propose a new end-to-end model for photorealistic style transfer that is both fast and inherently generates photorealistic results. The core of our approach is a feed-forward neural network that learns local edge-aware affine transforms that automatically obey the photorealism constraint. When trained on a diverse set of images and a variety of styles, our model can robustly apply style transfer to an arbitrary pair of input images. Compared to the state of the art, our method produces visually superior results and is three orders of magnitude faster, enabling real-time performance at 4K on a mobile phone. We validate our method with ablation and user studies.
Accelerometer-based (and by extension other inertial sensors) research for Human Activity Recognition (HAR) is a dead-end. This sensor does not offer enough information for us to progress in the core domain of HAR - to recognize everyday activities from sensor data. Despite continued and prolonged efforts in improving feature engineering and machine learning models, the activities that we can recognize reliably have only expanded slightly and many of the same flaws of early models are still present today. Instead of relying on acceleration data, we should instead consider modalities with much richer information - a logical choice are images. With the rapid advance in image sensing hardware and modelling techniques, we believe that a widespread adoption of image sensors will open many opportunities for accurate and robust inference across a wide spectrum of human activities. In this paper, we make the case for imagers in place of accelerometers as the default sensor for human activity recognition. Our review of past works has led to the observation that progress in HAR had stalled, caused by our reliance on accelerometers. We further argue for the suitability of images for activity recognition by illustrating their richness of information and the marked progress in computer vision. Through a feasibility analysis, we find that deploying imagers and CNNs on device poses no substantial burden on modern mobile hardware. Overall, our work highlights the need to move away from accelerometers and calls for further exploration of using imagers for activity recognition.
Data privacy protection is an important research area, which is especially critical in this big data era. To a large extent, the privacy of visual classification tasks is mainly in the one-to-one mapping between image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios. In this paper, we propose Mapping Distortion Protection (MDP) and its augmentation-based extension (AugMDP) to protect the data privacy by modifying the original dataset. In MDP, the label of the modified image does not match the ground-truth mapping, yet DNNs can still learn the ground-truth relation even when the provided mapping is distorted. As such, this method protects privacy when the dataset is leaked. Extensive experiments are conducted on CIFAR-10 and restricted CASIA-WebFace dataset, which verifies the effectiveness and feasibility of the method.
Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better represented in the training data. This happens because of the generalization that classifiers have to make. It is simpler to fit the majority groups as this fit is more important to overall error. We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened, minorities become majorities and vice versa. We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples. We experiment with the equalized odds bias measure on tabular data as well as image data (CelebA and Diversity in Faces datasets). Contrastive examples allow us to expose correlations between group membership and other seemingly neutral features. Whenever a causal graph is available, we can put those contrastive examples in the perspective of counterfactuals.
Deep learning-based recommendation models are used pervasively and broadly, for example, to recommend movies, products, or other information most relevant to users, in order to enhance the user experience. Among various application domains which have received significant industry and academia research attention, such as image classification, object detection, language and speech translation, the performance of deep learning-based recommendation models is less well explored, even though recommendation tasks unarguably represent significant AI inference cycles at large-scale datacenter fleets. To advance the state of understanding and enable machine learning system development and optimization for the commerce domain, we aim to define an industry-relevant recommendation benchmark for the MLPerf Training andInference Suites. The paper synthesizes the desirable modeling strategies for personalized recommendation systems. We lay out desirable characteristics of recommendation model architectures and data sets. We then summarize the discussions and advice from the MLPerf Recommendation Advisory Board.
This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed a human evaluation in order to estimate the usefulness of multimodal data for human machine translation and image description generation. Our systems obtained the best results for both tasks according to the automatic evaluation metrics BLEU and METEOR.
Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important field of research. In computer vision, unsupervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object categories among images in a collection, following the work of Cho et al. 2015. We show that the original approach can be reformulated and solved as a proper optimization problem. Experiments on several benchmarks establish the merit of our approach.
Artificial intelligence (AI) enabled radiomics has evolved immensely especially in the field of oncology. Radiomics provide assistancein diagnosis of cancer, planning of treatment strategy, and predictionof survival. Radiomics in neuro-oncology has progressed significantly inthe recent past. Deep learning has outperformed conventional machinelearning methods in most image-based applications. Convolutional neu-ral networks (CNNs) have seen some popularity in radiomics, since theydo not require hand-crafted features and can automatically extract fea-tures during the learning process. In this regard, it is observed that CNNbased radiomics could provide state-of-the-art results in neuro-oncology,similar to the recent success of such methods in a wide spectrum ofmedical image analysis applications. Herein we present a review of the most recent best practices and establish the future trends for AI enabled radiomics in neuro-oncology.
Computed Tomography (CT) takes X-ray measurements on the subjects to reconstruct tomographic images. As X-ray is radioactive, it is desirable to control the total amount of dose of X-ray for safety concerns. Therefore, we can only select a limited number of measurement angles and assign each of them limited amount of dose. Traditional methods such as compressed sensing usually randomly select the angles and equally distribute the allowed dose on them. In most CT reconstruction models, the emphasize is on designing effective image representations, while much less emphasize is on improving the scanning strategy. The simple scanning strategy of random angle selection and equal dose distribution performs well in general, but they may not be ideal for each individual subject. It is more desirable to design a personalized scanning strategy for each subject to obtain better reconstruction result. In this paper, we propose to use Reinforcement Learning (RL) to learn a personalized scanning policy to select the angles and the dose at each chosen angle for each individual subject. We first formulate the CT scanning process as an MDP, and then use modern deep RL methods to solve it. The learned personalized scanning strategy not only leads to better reconstruction results, but also shows strong generalization to be combined with different reconstruction algorithms.
Cell segmentation and tracking allow us to extract a plethora of cell attributes from bacterial time-lapse cell movies, thus promoting computational modeling and simulation of biological processes down to the single-cell level. However, to analyze successfully complex cell movies, imaging multiple interacting bacterial clones as they grow and merge to generate overcrowded bacterial communities with thousands of cells in the field of view, segmentation results should be near perfect to warrant good tracking results. We introduce here a fully automated closed-loop bio-inspired computational strategy that exploits prior knowledge about the expected structure of a colony's lineage tree to locate and correct segmentation errors in analyzed movie frames. We show that this correction strategy is effective, resulting in improved cell tracking and consequently trustworthy deep colony lineage trees. Our image analysis approach has the unique capability to keep tracking cells even after clonal subpopulations merge in the movie. This enables the reconstruction of the complete Forest of Lineage Trees (FLT) representation of evolving multi-clonal bacterial communities. Moreover, the percentage of valid cell trajectories extracted from the image analysis almost doubles after segmentation correction. This plethora of trustworthy data extracted from a complex cell movie analysis enables single-cell analytics as a tool for addressing compelling questions for human health, such as understanding the role of single-cell stochasticity in antibiotics resistance without losing site of the inter-cellular interactions and microenvironment effects that may shape it.