面部额叶化包括从任意观看的脸部合成正面观看的脸部。本文的主要贡献是一种额叶化方法，该方法可以保留非刚性面部变形，以提高视觉辅助语音交流的性能。该方法在（i）〜刚性转换（刻度，旋转和翻译）和（ii）〜任意观看的面部和面部模型之间的非rigid变形之间交替交替。该方法具有两个重要的优点：它可以处理数据中的非高斯错误，并结合了动态的面部变形模型。为此，我们将广义的学生T-分布与线性动态系统结合使用，以说明僵化的头部运动和由语音产生引起的时变面部变形。我们建议使用零均值的归一化互相关（ZNCC）评分来评估该方法保留面部表情的能力。根据传统的几何模型或深度学习，对该方法进行了彻底评估并与几种最先进的方法进行了比较。此外，我们表明，当将这种方法纳入深度学习管道中时，即唇部阅读和语音增强，将单词识别和语音智能分数提高了相当大的差距。可以在https://team.inria.fr/robotlearn/research/facefrontalization-benchmark/上访问补充材料

在概率深层生成模型中构建潜在空间，例如变异自动编码器（VAE），对于产生更具表现力的模型和可解释的表示并避免过度拟合非常重要。实现这一目标的一种方法是对潜在变量（例如，通过Laplace先验）施加稀疏性约束。但是，这种方法通常会使训练阶段变得复杂，并且它们牺牲了重建质量以促进稀疏性。在本文中，我们提出了一种简单而有效的方法，可以通过启动稀疏字典模型来构建潜在空间，该模型假设每个潜在代码可以写成词典的列的稀疏线性组合。特别是，我们利用了一种计算高效且无调的方法，该方法依赖于具有可学习方差的零均值高斯潜在方法。我们得出了训练模型的变异推理方案。语音生成建模的实验证明了所提出的方法比竞争技术的优势，因为它会促进稀疏性，同时又不恶化输出语音质量。

Differentiable Search Indices (DSIs) encode a corpus of documents in the parameters of a model and use the same model to map queries directly to relevant document identifiers. Despite the strong performance of DSI models, deploying them in situations where the corpus changes over time is computationally expensive because reindexing the corpus requires re-training the model. In this work, we introduce DSI++, a continual learning challenge for DSI to incrementally index new documents while being able to answer queries related to both previously and newly indexed documents. Across different model scales and document identifier representations, we show that continual indexing of new documents leads to considerable forgetting of previously indexed documents. We also hypothesize and verify that the model experiences forgetting events during training, leading to unstable learning. To mitigate these issues, we investigate two approaches. The first focuses on modifying the training dynamics. Flatter minima implicitly alleviate forgetting, so we optimize for flatter loss basins and show that the model stably memorizes more documents (+12\%). Next, we introduce a generative memory to sample pseudo-queries for documents and supplement them during continual indexing to prevent forgetting for the retrieval task. Extensive experiments on novel continual indexing benchmarks based on Natural Questions (NQ) and MS MARCO demonstrate that our proposed solution mitigates forgetting by a significant margin. Concretely, it improves the average Hits@10 by $+21.1\%$ over competitive baselines for NQ and requires $6$ times fewer model updates compared to re-training the DSI model for incrementally indexing five corpora in a sequence.

One of the main challenges in deep learning-based underwater image enhancement is the limited availability of high-quality training data. Underwater images are difficult to capture and are often of poor quality due to the distortion and loss of colour and contrast in water. This makes it difficult to train supervised deep learning models on large and diverse datasets, which can limit the model's performance. In this paper, we explore an alternative approach to supervised underwater image enhancement. Specifically, we propose a novel unsupervised underwater image enhancement framework that employs a conditional variational autoencoder (cVAE) to train a deep learning model with probabilistic adaptive instance normalization (PAdaIN) and statistically guided multi-colour space stretch that produces realistic underwater images. The resulting framework is composed of a U-Net as a feature extractor and a PAdaIN to encode the uncertainty, which we call UDnet. To improve the visual quality of the images generated by UDnet, we use a statistically guided multi-colour space stretch module that ensures visual consistency with the input image and provides an alternative to training using a ground truth image. The proposed model does not need manual human annotation and can learn with a limited amount of data and achieves state-of-the-art results on underwater images. We evaluated our proposed framework on eight publicly-available datasets. The results show that our proposed framework yields competitive performance compared to other state-of-the-art approaches in quantitative as well as qualitative metrics. Code available at https://github.com/alzayats/UDnet .

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Training large, deep neural networks to convergence can be prohibitively expensive. As a result, often only a small selection of popular, dense models are reused across different contexts and tasks. Increasingly, sparsely activated models, which seek to decouple model size from computation costs, are becoming an attractive alternative to dense models. Although more efficient in terms of quality and computation cost, sparse models remain data-hungry and costly to train from scratch in the large scale regime. In this work, we propose sparse upcycling -- a simple way to reuse sunk training costs by initializing a sparsely activated Mixture-of-Experts model from a dense checkpoint. We show that sparsely upcycled T5 Base, Large, and XL language models and Vision Transformer Base and Large models, respectively, significantly outperform their dense counterparts on SuperGLUE and ImageNet, using only ~50% of the initial dense pretraining sunk cost. The upcycled models also outperform sparse models trained from scratch on 100% of the initial dense pretraining computation budget.

Cardiac resynchronization therapy (CRT) is a treatment that is used to compensate for irregularities in the heartbeat. Studies have shown that this treatment is more effective in heart patients with left bundle branch block (LBBB) arrhythmia. Therefore, identifying this arrhythmia is an important initial step in determining whether or not to use CRT. On the other hand, traditional methods for detecting LBBB on electrocardiograms (ECG) are often associated with errors. Thus, there is a need for an accurate method to diagnose this arrhythmia from ECG data. Machine learning, as a new field of study, has helped to increase human systems' performance. Deep learning, as a newer subfield of machine learning, has more power to analyze data and increase systems accuracy. This study presents a deep learning model for the detection of LBBB arrhythmia from 12-lead ECG data. This model consists of 1D dilated convolutional layers. Attention mechanism has also been used to identify important input data features and classify inputs more accurately. The proposed model is trained and validated on a database containing 10344 12-lead ECG samples using the 10-fold cross-validation method. The final results obtained by the model on the 12-lead ECG data are as follows. Accuracy: 98.80+-0.08%, specificity: 99.33+-0.11 %, F1 score: 73.97+-1.8%, and area under the receiver operating characteristics curve (AUC): 0.875+-0.0192. These results indicate that the proposed model in this study can effectively diagnose LBBB with good efficiency and, if used in medical centers, will greatly help diagnose this arrhythmia and early treatment.

The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common approaches, but current methods have considerable limitations.For example, fine-tuning an existing policy frequently fails, as the policy can degrade rapidly early in training. In a similar vein, distillation of expert behavior can lead to poor results when given sub-optimal experts. We compare several common approaches for skill transfer on multiple domains including changes in task and system dynamics. We identify how existing methods can fail and introduce an alternative approach to mitigate these problems. Our approach learns to sequence existing temporally-extended skills for exploration but learns the final policy directly from the raw experience. This conceptual split enables rapid adaptation and thus efficient data collection but without constraining the final solution.It significantly outperforms many classical methods across a suite of evaluation tasks and we use a broad set of ablations to highlight the importance of differentc omponents of our method.

Chromosome analysis is essential for diagnosing genetic disorders. For hematologic malignancies, identification of somatic clonal aberrations by karyotype analysis remains the standard of care. However, karyotyping is costly and time-consuming because of the largely manual process and the expertise required in identifying and annotating aberrations. Efforts to automate karyotype analysis to date fell short in aberration detection. Using a training set of ~10k patient specimens and ~50k karyograms from over 5 years from the Fred Hutchinson Cancer Center, we created a labeled set of images representing individual chromosomes. These individual chromosomes were used to train and assess deep learning models for classifying the 24 human chromosomes and identifying chromosomal aberrations. The top-accuracy models utilized the recently introduced Topological Vision Transformers (TopViTs) with 2-level-block-Toeplitz masking, to incorporate structural inductive bias. TopViT outperformed CNN (Inception) models with >99.3% accuracy for chromosome identification, and exhibited accuracies >99% for aberration detection in most aberrations. Notably, we were able to show high-quality performance even in "few shot" learning scenarios. Incorporating the definition of clonality substantially improved both precision and recall (sensitivity). When applied to "zero shot" scenarios, the model captured aberrations without training, with perfect precision at >50% recall. Together these results show that modern deep learning models can approach expert-level performance for chromosome aberration detection. To our knowledge, this is the first study demonstrating the downstream effectiveness of TopViTs. These results open up exciting opportunities for not only expediting patient results but providing a scalable technology for early screening of low-abundance chromosomal lesions.

Multi-objective feature selection is one of the most significant issues in the field of pattern recognition. It is challenging because it maximizes the classification performance and, at the same time, minimizes the number of selected features, and the mentioned two objectives are usually conflicting. To achieve a better Pareto optimal solution, metaheuristic optimization methods are widely used in many studies. However, the main drawback is the exploration of a large search space. Another problem with multi-objective feature selection approaches is the interaction between features. Selecting correlated features has negative effect on classification performance. To tackle these problems, we present a novel multi-objective feature selection method that has several advantages. Firstly, it considers the interaction between features using an advanced probability scheme. Secondly, it is based on the Pareto Archived Evolution Strategy (PAES) method that has several advantages such as simplicity and its speed in exploring the solution space. However, we improve the structure of PAES in such a way that generates the offsprings, intelligently. Thus, the proposed method utilizes the introduced probability scheme to produce more promising offsprings. Finally, it is equipped with a novel strategy that guides it to find the optimum number of features through the process of evolution. The experimental results show a significant improvement in finding the optimal Pareto front compared to state-of-the-art methods on different real-world datasets.