使用文本，图像，音频，视频等多种方式的多模式深度学习系统，与单独的方式（即单向）系统相比，显示出更好的性能。多式联机学习涉及多个方面：表示，翻译，对齐，融合和共同学习。在当前多式联机学习状态下，假设是在训练和测试时间期间存在，对齐和无噪声。然而，在现实世界的任务中，通常，观察到一个或多个模式丢失，嘈杂，缺乏注释数据，具有不可靠的标签，并且在训练或测试中稀缺，或两者都稀缺。这种挑战是由称为多式联合学习的学习范例解决的。通过使用模态之间的知识传输，包括其表示和预测模型，通过从另一个（资源丰富的）方式利用来自另一（资源丰富的）模型的知识来帮助实现（资源差）模型的建模。共同学习是一个新兴地区，没有专注的评论，明确地关注共同学习所解决的所有挑战。为此，在这项工作中，我们对新兴的多式联合学习领域提供了全面的调查，尚未完整探讨。我们审查实施的实施，以克服一个或多个共同学习挑战，而不明确地将它们视为共同学习挑战。我们基于共同学习和相关实施解决的挑战，展示了多式联合学习的综合分类。用于包括最新的技术与一些应用程序和数据集一起审查。我们的最终目标是讨论挑战和观点以及未来工作的重要思想和方向，我们希望对整个研究界的有益，重点关注这一令人兴奋的领域。

Deep learning techniques with neural networks have been used effectively in computational fluid dynamics (CFD) to obtain solutions to nonlinear differential equations. This paper presents a physics-informed neural network (PINN) approach to solve the Blasius function. This method eliminates the process of changing the non-linear differential equation to an initial value problem. Also, it tackles the convergence issue arising in the conventional series solution. It is seen that this method produces results that are at par with the numerical and conventional methods. The solution is extended to the negative axis to show that PINNs capture the singularity of the function at $\eta=-5.69$

Recently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their achievement is proving slow to transition to widespread use in medical clinics because of robustness issues leading to low trust of clinicians to their results. Predicting run-time quality of segmentation masks can be useful to warn clinicians against poor results. Despite its importance, there are few studies on this problem. To address this gap, we propose a quality control method based on the agreement across decoders of a multi-view network, TMS-Net, measured by the cosine similarity. The network takes three view inputs resliced from the same 3D image along different axes. Different from previous multi-view networks, TMS-Net has a single encoder and three decoders, leading to better noise robustness, segmentation performance and run-time quality estimation in our experiments on the segmentation of the left atrium on STACOM 2013 and STACOM 2018 challenge datasets. We also present a way to generate poor segmentation masks by using noisy images generated with engineered noise and Rician noise to simulate undertraining, high anisotropy and poor imaging settings problems. Our run-time quality estimation method show a good classification of poor and good quality segmentation masks with an AUC reaching to 0.97 on STACOM 2018. We believe that TMS-Net and our run-time quality estimation method has a high potential to increase the thrust of clinicians to automatic image analysis tools.

Speech systems are sensitive to accent variations. This is especially challenging in the Indian context, with an abundance of languages but a dearth of linguistic studies characterising pronunciation variations. The growing number of L2 English speakers in India reinforces the need to study accents and L1-L2 interactions. We investigate the accents of Indian English (IE) speakers and report in detail our observations, both specific and common to all regions. In particular, we observe the phonemic variations and phonotactics occurring in the speakers' native languages and apply this to their English pronunciations. We demonstrate the influence of 18 Indian languages on IE by comparing the native language pronunciations with IE pronunciations obtained jointly from existing literature studies and phonetically annotated speech of 80 speakers. Consequently, we are able to validate the intuitions of Indian language influences on IE pronunciations by justifying pronunciation rules from the perspective of Indian language phonology. We obtain a comprehensive description in terms of universal and region-specific characteristics of IE, which facilitates accent conversion and adaptation of existing ASR and TTS systems to different Indian accents.

Developing and least developed countries face the dire challenge of ensuring that each child in their country receives required doses of vaccination, adequate nutrition and proper medication. International agencies such as UNICEF, WHO and WFP, among other organizations, strive to find innovative solutions to determine which child has received the benefits and which have not. Biometric recognition systems have been sought out to help solve this problem. To that end, this report establishes a baseline accuracy of a commercial contactless palmprint recognition system that may be deployed for recognizing children in the age group of one to five years old. On a database of contactless palmprint images of one thousand unique palms from 500 children, we establish SOTA authentication accuracy of 90.85% @ FAR of 0.01%, rank-1 identification accuracy of 99.0% (closed set), and FPIR=0.01 @ FNIR=0.3 for open-set identification using PalmMobile SDK from Armatura.

In this paper, we study the effect of a novel regularization scheme on contrastive language-image pre-trained (CLIP) models. Our approach is based on the observation that, in many domains, text tokens should only describe a small number of image regions and, likewise, each image region should correspond to only a few text tokens. In CLIP-style models, this implies that text-token embeddings should have high similarity to only a small number of image-patch embeddings for a given image-text pair. We formalize this observation using a novel regularization scheme that penalizes the entropy of the text-token to image-patch similarity scores. We qualitatively and quantitatively demonstrate that the proposed regularization scheme shrinks the text-token and image-patch similarity scores towards zero, thus achieving the desired effect. We demonstrate the promise of our approach in an important medical context where this underlying hypothesis naturally arises. Using our proposed approach, we achieve state of the art (SOTA) zero-shot performance on all tasks from the CheXpert chest x-ray dataset, outperforming an unregularized version of the model and several recently published self-supervised models.

Accomplishing safe and efficient driving is one of the predominant challenges in the controller design of connected automated vehicles (CAVs). It is often more convenient to address these goals separately and integrate the resulting controllers. In this study, we propose a controller integration scheme to fuse performance-based controllers and safety-oriented controllers safely for the longitudinal motion of a CAV. The resulting structure is compatible with a large class of controllers, and offers flexibility to design each controller individually without affecting the performance of the others. We implement the proposed safe integration scheme on a connected automated truck using an optimal-in-energy controller and a safety-oriented connected cruise controller. We validate the premise of the safe integration through experiments with a full-scale truck in two scenarios: a controlled experiment on a test track and a real-world experiment on a public highway. In both scenarios, we achieve energy efficient driving without violating safety.

Atrial Fibrillation (AF) is characterized by disorganised electrical activity in the atria and is known to be sustained by the presence of regions of fibrosis (scars) or functional cellular remodeling, both of which may lead to areas of slow conduction. Estimating the effective conductivity of the myocardium and identifying regions of abnormal propagation is therefore crucial for the effective treatment of AF. We hypothesise that the spatial distribution of tissue conductivity can be directly inferred from an array of concurrently acquired contact electrograms (EGMs). We generate a dataset of simulated cardiac AP propagation using randomised scar distributions and a phenomenological cardiac model and calculate contact electrograms at various positions on the field. A deep neural network, based on a modified U-net architecture, is trained to estimate the location of the scar and quantify conductivity of the tissue with a Jaccard index of $91$%. We adapt a wavelet-based surrogate testing analysis to confirm that the inferred conductivity distribution is an accurate representation of the ground truth input to the model. We find that the root mean square error (RMSE) between the ground truth and our predictions is significantly smaller ($p_{val}=0.007$) than the RMSE between the ground truth and surrogate samples.

The problem of tensor completion has applications in healthcare, computer vision, and other domains. However, past approaches to tensor completion have faced a tension in that they either have polynomial-time computation but require exponentially more samples than the information-theoretic rate, or they use fewer samples but require solving NP-hard problems for which there are no known practical algorithms. A recent approach, based on integer programming, resolves this tension for nonnegative tensor completion. It achieves the information-theoretic sample complexity rate and deploys the Blended Conditional Gradients algorithm, which requires a linear (in numerical tolerance) number of oracle steps to converge to the global optimum. The tradeoff in this approach is that, in the worst case, the oracle step requires solving an integer linear program. Despite this theoretical limitation, numerical experiments show that this algorithm can, on certain instances, scale up to 100 million entries while running on a personal computer. The goal of this paper is to further enhance this algorithm, with the intention to expand both the breadth and scale of instances that can be solved. We explore several variants that can maintain the same theoretical guarantees as the algorithm, but offer potentially faster computation. We consider different data structures, acceleration of gradient descent steps, and the use of the Blended Pairwise Conditional Gradients algorithm. We describe the original approach and these variants, and conduct numerical experiments in order to explore various tradeoffs in these algorithmic design choices.

The use of vision transformers (ViT) in computer vision is increasing due to limited inductive biases (e.g., locality, weight sharing, etc.) and increased scalability compared to other deep learning methods. This has led to some initial studies on the use of ViT for biometric recognition, including fingerprint recognition. In this work, we improve on these initial studies for transformers in fingerprint recognition by i.) evaluating additional attention-based architectures, ii.) scaling to larger and more diverse training and evaluation datasets, and iii.) combining the complimentary representations of attention-based and CNN-based embeddings for improved state-of-the-art (SOTA) fingerprint recognition (both authentication and identification). Our combined architecture, AFR-Net (Attention-Driven Fingerprint Recognition Network), outperforms several baseline transformer and CNN-based models, including a SOTA commercial fingerprint system, Verifinger v12.3, across intra-sensor, cross-sensor, and latent to rolled fingerprint matching datasets. Additionally, we propose a realignment strategy using local embeddings extracted from intermediate feature maps within the networks to refine the global embeddings in low certainty situations, which boosts the overall recognition accuracy significantly across each of the models. This realignment strategy requires no additional training and can be applied as a wrapper to any existing deep learning network (including attention-based, CNN-based, or both) to boost its performance.