Recent deep learning models have attracted substantial attention in infant brain analysis. These models have performed state-of-the-art performance, such as semi-supervised techniques (e.g., Temporal Ensembling, mean teacher). However, these models depend on an encoder-decoder structure with stacked local operators to gather long-range information, and the local operators limit the efficiency and effectiveness. Besides, the $MRI$ data contain different tissue properties ($TPs$) such as $T1$ and $T2$. One major limitation of these models is that they use both data as inputs to the segment process, i.e., the models are trained on the dataset once, and it requires much computational and memory requirements during inference. In this work, we address the above limitations by designing a new deep-learning model, called 3D-DenseUNet, which works as adaptable global aggregation blocks in down-sampling to solve the issue of spatial information loss. The self-attention module connects the down-sampling blocks to up-sampling blocks, and integrates the feature maps in three dimensions of spatial and channel, effectively improving the representation potential and discriminating ability of the model. Additionally, we propose a new method called Two Independent Teachers ($2IT$), that summarizes the model weights instead of label predictions. Each teacher model is trained on different types of brain data, $T1$ and $T2$, respectively. Then, a fuse model is added to improve test accuracy and enable training with fewer parameters and labels compared to the Temporal Ensembling method without modifying the network architecture. Empirical results demonstrate the effectiveness of the proposed method. The code is available at https://github.com/AfifaKhaled/Two-Independent-Teachers-are-Better-Role-Model.

Generative Models (GMs) have attracted considerable attention due to their tremendous success in various domains, such as computer vision where they are capable to generate impressive realistic-looking images. Likelihood-based GMs are attractive due to the possibility to generate new data by a single model evaluation. However, they typically achieve lower sample quality compared to state-of-the-art score-based diffusion models (DMs). This paper provides a significant step in the direction of addressing this limitation. The idea is to borrow one of the strengths of score-based DMs, which is the ability to perform accurate density estimation in low-density regions and to address manifold overfitting by means of data mollification. We connect data mollification through the addition of Gaussian noise to Gaussian homotopy, which is a well-known technique to improve optimization. Data mollification can be implemented by adding one line of code in the optimization loop, and we demonstrate that this provides a boost in generation quality of likelihood-based GMs, without computational overheads. We report results on image data sets with popular likelihood-based GMs, including variants of variational autoencoders and normalizing flows, showing large improvements in FID score.

Distribution shifts are common in real-world datasets and can affect the performance and reliability of deep learning models. In this paper, we study two types of distribution shifts: diversity shifts, which occur when test samples exhibit patterns unseen during training, and correlation shifts, which occur when test data present a different correlation between seen invariant and spurious features. We propose an integrated protocol to analyze both types of shifts using datasets where they co-exist in a controllable manner. Finally, we apply our approach to a real-world classification problem of skin cancer analysis, using out-of-distribution datasets and specialized bias annotations. Our protocol reveals three findings: 1) Models learn and propagate correlation shifts even with low-bias training; this poses a risk of accumulating and combining unaccountable weak biases; 2) Models learn robust features in high- and low-bias scenarios but use spurious ones if test samples have them; this suggests that spurious correlations do not impair the learning of robust features; 3) Diversity shift can reduce the reliance on spurious correlations; this is counter intuitive since we expect biased models to depend more on biases when invariant features are missing. Our work has implications for distribution shift research and practice, providing new insights into how models learn and rely on spurious correlations under different types of shifts.

In the ever-evolving landscape of Artificial Intelligence (AI), the synergy between generative AI and Software Engineering emerges as a transformative frontier. This whitepaper delves into the unexplored realm, elucidating how generative AI techniques can revolutionize software development. Spanning from project management to support and updates, we meticulously map the demands of each development stage and unveil the potential of generative AI in addressing them. Techniques such as zero-shot prompting, self-consistency, and multimodal chain-of-thought are explored, showcasing their unique capabilities in enhancing generative AI models. The significance of vector embeddings, context, plugins, tools, and code assistants is underscored, emphasizing their role in capturing semantic information and amplifying generative AI capabilities. Looking ahead, this intersection promises to elevate productivity, improve code quality, and streamline the software development process. This whitepaper serves as a guide for stakeholders, urging discussions and experiments in the application of generative AI in Software Engineering, fostering innovation and collaboration for a qualitative leap in the efficiency and effectiveness of software development.

We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/

The electrocardiogram (ECG) is routinely used in cardiology, though its interpretation is confounded by anatomical variability. A novel, automated computational pipeline enables quantification of torso-ventricular anatomy metrics from magnetic resonance imaging, and comparison to ECG characteristics. Sex and myocardial infarction differences are investigated based on 1051 healthy and 425 post-MI subjects from UK Biobank. Smaller ventricles in females explain ~50% of shorter QRS durations than in males, and contribute to lower STJ amplitudes in females (also due to more superior and posterior position). In females, torso-ventricular anatomy, particularly from larger BMI, is a stronger modulator of T wave amplitude reductions and left-deviated R axis angles in post-MI than in males. Thus, female MI phenotype is less reflective of pathology, and baseline STJ amplitudes and QRS durations are further from clinical thresholds. Therefore, quantification of anatomical sex-differences and impact on ECG in health and disease is critical to avoid clinical sex-bias.

This review gives an extensive overview of evaluation methods for task-oriented dialogue systems, paying special attention to practical applications of dialogue systems, for example for customer service. The review (1) provides an overview of the used constructs and metrics in previous work, (2) discusses challenges in the context of dialogue system evaluation and (3) develops a research agenda for the future of dialogue system evaluation. We conducted a systematic review of four databases (ACL, ACM, IEEE and Web of Science), which after screening resulted in 122 studies. Those studies were carefully analysed for the constructs and methods they proposed for evaluation. We found a wide variety in both constructs and methods. Especially the operationalisation is not always clearly reported. We hope that future work will take a more critical approach to the operationalisation and specification of the used constructs. To work towards this aim, this review ends with recommendations for evaluation and suggestions for outstanding questions.

To ensure resilient neural network processing on even unreliable hardware, comprehensive reliability analysis against various hardware faults is generally required before the deep neural network models are deployed, and efficient error injection tools are highly demanded. However, most existing fault injection tools remain rather limited to basic fault injection to neurons and fail to provide fine-grained vulnerability analysis capability. In addition, many of the fault injection tools still need to change the neural network models and make the fault injection closely coupled with normal neural network processing, which further complicates the use of the fault injection tools and slows down the fault simulation. In this work, we propose MRFI, a highly configurable multi-resolution fault injection tool for deep neural networks. It enables users to modify an independent fault configuration file rather than neural network models for the fault injection and vulnerability analysis. Particularly, it integrates extensive fault analysis functionalities from different perspectives and enables multi-resolution investigation of the vulnerability of neural networks. In addition, it does not modify the major neural network computing framework of PyTorch. Hence, it allows parallel processing on GPUs naturally and exhibits fast fault simulation according to our experiments.

This paper presents VoxCeleb-ESP, a collection of pointers and timestamps to YouTube videos facilitating the creation of a novel speaker recognition dataset. VoxCeleb-ESP captures real-world scenarios, incorporating diverse speaking styles, noises, and channel distortions. It includes 160 Spanish celebrities spanning various categories, ensuring a representative distribution across age groups and geographic regions in Spain. We provide two speaker trial lists for speaker identification tasks, each of them with same-video or different-video target trials respectively, accompanied by a cross-lingual evaluation of ResNet pretrained models. Preliminary speaker identification results suggest that the complexity of the detection task in VoxCeleb-ESP is equivalent to that of the original and much larger VoxCeleb in English. VoxCeleb-ESP contributes to the expansion of speaker recognition benchmarks with a comprehensive and diverse dataset for the Spanish language.

Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A strategy to improve label quality is to ask multiple annotators to label the same item and aggregate their labels. Many aggregation models have been proposed for categorical or numerical annotation tasks, but far less work has considered more complex annotation tasks involving open-ended, multivariate, or structured responses. While a variety of bespoke models have been proposed for specific tasks, our work is the first to introduce aggregation methods that generalize across many diverse complex tasks, including sequence labeling, translation, syntactic parsing, ranking, bounding boxes, and keypoints. This generality is achieved by devising a task-agnostic method to model distances between labels rather than the labels themselves. This article extends our prior work with investigation of three new research questions. First, how do complex annotation properties impact aggregation accuracy? Second, how should a task owner navigate the many modeling choices to maximize aggregation accuracy? Finally, what diagnoses can verify that aggregation models are specified correctly for the given data? To understand how various factors impact accuracy and to inform model selection, we conduct simulation studies and experiments on real, complex datasets. Regarding testing, we introduce unit tests for aggregation models and present a suite of such tests to ensure that a given model is not mis-specified and exhibits expected behavior. Beyond investigating these research questions above, we discuss the foundational concept of annotation complexity, present a new aggregation model as a bridge between traditional models and our own, and contribute a new semi-supervised learning method for complex label aggregation that outperforms prior work.