Today's interactive devices such as smart-phone assistants and smart speakers often deal with short-duration speech segments. As a result, speaker recognition systems integrated into such devices will be much better suited with models capable of performing the recognition task with short-duration utterances. In this paper, a new deep neural network, UtterIdNet, capable of performing speaker recognition with short speech segments is proposed. Our proposed model utilizes a novel architecture that makes it suitable for short-segment speaker recognition through an efficiently increased use of information in short speech segments. UtterIdNet has been trained and tested on the V oxCeleb datasets, the latest benchmarks in speaker recognition. Evaluations for different segment durations show consistent and stable performance for short segments, with significant improvement over the previous models for segments of 2 seconds, 1 second, and especially sub-second durations (250 ms and 500 ms).

Adversarial examples have recently proven to be able to fool deep learning methods by adding carefully crafted small perturbation to the input space image. In this paper, we study the possibility of generating adversarial examples for code-based iris recognition systems. Since generating adversarial examples requires back-propagation of the adversarial loss, conventional filter bank-based iris-code generation frameworks cannot be employed in such a setup. Therefore, to compensate for this shortcoming, we propose to train a deep auto-encoder surrogate network to mimic the conventional iris code generation procedure. This trained surrogate network is then deployed to generate the adversarial examples using the iterative gradient sign method algorithm. We consider non-targeted and targeted attacks through three attack scenarios. Considering these attacks, we study the possibility of fooling an iris recognition system in white-box and black-box frameworks.

We investigate the robustness properties of ResNeXt image recognition models trained with billion scale weakly-supervised data (ResNeXt WSL models). These models, recently made public by Facebook AI, were trained on 1B images from Instagram and fine-tuned on ImageNet. We show that these models display an unprecedented degree of robustness against common image corruptions and perturbations, as measured by the ImageNet-C and ImageNet-P benchmarks. The largest of the released models, in particular, achieves state-of-the-art results on both ImageNet-C and ImageNet-P by a large margin. The gains on ImageNet-C and ImageNet-P far outpace the gains on ImageNet validation accuracy, suggesting the former as more useful benchmarks to measure further progress in image recognition. Remarkably, the ResNeXt WSL models even achieve a limited degree of adversarial robustness against state-of-the-art white-box attacks (10-step PGD attacks). However, in contrast to adversarially trained models, the robustness of the ResNeXt WSL models rapidly declines with the number of PGD steps, suggesting that these models do not achieve genuine adversarial robustness. Visualization of the learned features also confirms this conclusion. Finally, we show that although the ResNeXt WSL models are more shape-biased than comparable ImageNet-trained models in a shape-texture cue conflict experiment, they still remain much more texture-biased than humans and their accuracy on the recently introduced "natural adversarial examples" (ImageNet-A) also remains low, suggesting that they share many of the underlying characteristics of ImageNet-trained models that make these benchmarks challenging.

Machine Learning (ML) represents a massive change in the computing industry. It is a long-term trend that offers the potential for significant advantages for many enterprises. Accurate prediction is critical for practically all enterprises. Without a degree of confidence in business forecasting, organizations would have a difficult time delivering successful products and services in a cost-effective manner. Machine Learning provides the capability to offer deep predictive and prescriptive decision-making intelligence.

AI technologies have the potential to dramatically impact the lives of people with disabilities (PWD). Indeed, improving the lives of PWD is a motivator for many state-of-the-art AI systems, such as automated speech recognition tools that can caption videos for people who are deaf and hard of hearing, or language prediction algorithms that can augment communication for people with speech or cognitive disabilities. However, widely deployed AI systems may not work properly for PWD, or worse, may actively discriminate against them. These considerations regarding fairness in AI for PWD have thus far received little attention. In this position paper, we identify potential areas of concern regarding how several AI technology categories may impact particular disability constituencies if care is not taken in their design, development, and testing. We intend for this risk assessment of how various classes of AI might interact with various classes of disability to provide a roadmap for future research that is needed to gather data, test these hypotheses, and build more inclusive algorithms.

Medical image registration is one of the key processing steps for biomedical image analysis such as cancer diagnosis. Recently, deep learning based supervised and unsupervised image registration methods have been extensively studied due to its excellent performance in spite of ultra-fast computational time compared to the classical approaches. In this paper, we present a novel unsupervised medical image registration method that trains deep neural network for deformable registration of 3D volumes using a cycle-consistency. Thanks to the cycle consistency, the proposed deep neural networks can take diverse pair of image data with severe deformation for accurate registration. Experimental results using multiphase liver CT images demonstrate that our method provides very precise 3D image registration within a few seconds, resulting in more accurate cancer size estimation.

Multi-view learning (MVL) is a strategy for fusing data from different sources or subsets. Canonical correlation analysis (CCA) is very important in MVL, whose main idea is to map data from different views onto a common space with the maximum correlation. The traditional CCA can only be used to calculate the linear correlation between two views. Moreover, it is unsupervised, and the label information is wasted in supervised learning tasks. Many nonlinear, supervised, or generalized extensions have been proposed to overcome these limitations. However, to our knowledge, there is no up-to-date overview of these approaches. This paper fills this gap, by providing a comprehensive overview of many classical and latest CCA approaches, and describing their typical applications in pattern recognition, multi-modal retrieval and classification, and multi-view embedding.

The American Bureau of Shipping recently collaborated with Google Cloud and software engineers SoftServe to use artificial intelligence (AI) models to detect levels of corrosion and marine coatings breakdowns on brown- and bluewater vessels. The pilot project is aimed at developing image recognition software tools that can examine early signs of degradation in hull structures, to avoid unsafe working conditions, unscheduled maintenance and resulting operational downtime. The effort demonstrated how AI can support early detection of structural anomalies that are usually found through traditional, visual inspections. The project was focused on corrosion and coatings failures, but ABS engineers believe the new tools could also be used to detect stress fractures and larger hull deformations. These AI techniques -- in tandem with advanced data algorithms -- could be used to analyze images over time to understand the trends in corrosion and asset fatigue that would support a transition to more efficient class and maintenance regimes for everything from workboats to offshore structures.

Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans categorize objects, these approaches have not yet made use of any taxonomical organization of class labels. With such an approach, for instance, we may see why a chimpanzee is classified as a chimpanzee, but not why it was considered to be a primate or even an animal. In this work we introduce a model that uses hierarchically organized prototypes to classify objects at every level in a predefined taxonomy. Hence, we may find distinct explanations for the prediction an image receives at each level of the taxonomy. The hierarchical prototypes enable the model to perform another important task: interpretably classifying images from previously unseen classes at the level of the taxonomy to which they correctly relate, e.g. classifying a hand gun as a weapon, when the only weapons in the training data are rifles. With a subset of ImageNet, we test our model against its counterpart black-box model on two tasks: 1) classification of data from familiar classes, and 2) classification of data from previously unseen classes at the appropriate level in the taxonomy. We find that our model performs approximately as well as its counterpart black-box model while allowing for each classification to be interpreted.

Artificial intelligence (AI) and its many related applications (ie, big data, deep analytics, machine learning) have entered medicine's "magic bullet" phase. Desperate for a solution for the never-ending challenges of cost, quality, equity, and access, a steady stream of books, articles, and corporate pronouncements makes it seem like health care is on the cusp of an "AI revolution," one that will finally result in high-value care. While AI has been responsible for some stunning advances, particularly in the area of visual pattern recognition,1-3 a major challenge will be in converting AI-derived predictions or recommendations into effective action.