无监督语义分割的任务旨在将像素聚集到语义上有意义的群体中。具体而言，分配给同一群集的像素应共享高级语义属性，例如其对象或零件类别。本文介绍了MaskDistill：基于三个关键想法的无监督语义细分的新颖框架。首先，我们提倡一种数据驱动的策略，以生成对象掩模作为语义分割事先的像素分组。这种方法省略了手工制作的先验，这些先验通常是为特定场景组成而设计的，并限制了竞争框架的适用性。其次，MaskDistill将对象掩盖簇簇以获取伪地真相，以训练初始对象分割模型。第三，我们利用此模型过滤出低质量的对象掩模。这种策略减轻了我们像素分组中的噪声，并导致了我们用来训练最终分割模型的干净掩模集合。通过组合这些组件，我们可以大大优于以前的作品，用于对Pascal（+11％MIOU）和COCO（+4％Mask AP50）进行无监督的语义分割。有趣的是，与现有方法相反，我们的框架不在低级图像提示上，也不限于以对象为中心的数据集。代码和型号将提供。

视觉反事实解释用来自干扰器图像的区域代替了查询图像中的图像区域，以使系统对转换图像的决策变为干扰器类。在这项工作中，我们提出了一个新颖的框架，用于根据两个关键思想计算视觉反事实说明。首先，我们强制执行替换和替换区域包含相同的语义部分，从而产生了更加一致的解释。其次，我们以计算上有效的方式使用多个干扰器图像，并获得更少的区域替代方法的更多歧视性解释。我们的方法在语义上一致性高27％，并且比三个细粒图像识别数据集的竞争方法要快27％。我们通过机器教学实验来强调反事实对现有作品的实用性，在这些实验中，我们教人类对不同的鸟类进行分类。我们还用零件和属性的词汇来补充我们的解释，这些零件和属性对系统的决定有所帮助。在此任务中，当使用相对于现有作品的反事实解释时，我们将获得最新的结果，从而增强了语义一致的解释的重要性。源代码可从https://github.com/facebookresearch/visual-counterfactuals获得。

对比自我监督的学习已经超越了许多下游任务的监督预测，如分割和物体检测。但是，当前的方法仍然主要应用于像想象成的策划数据集。在本文中，我们首先研究数据集中的偏差如何影响现有方法。我们的研究结果表明，目前的对比方法令人惊讶地工作：（i）对象与场景为中心，（ii）统一与长尾和（iii）一般与域特定的数据集。其次，鉴于这种方法的一般性，我们尝试通过微小的修改来实现进一步的收益。我们展示了学习额外的修正 - 通过使用多尺度裁剪，更强的增强和最近的邻居 - 改善了表示。最后，我们观察Moco在用多作物策略训练时学习空间结构化表示。表示可以用于语义段检索和视频实例分段，而不会FineTuning。此外，结果与专门模型相提并论。我们希望这项工作将成为其他研究人员的有用研究。代码和模型可在https://github.com/wvanganebleke/revisiting-contrastive-ssl上获得。

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. In doing so, we remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by large margins, in particular +26.6% on CI-FAR10, +25.0% on CIFAR100-20 and +21.3% on STL10 in terms of classification accuracy. Furthermore, our method is the first to perform well on a large-scale dataset for image classification. In particular, we obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime without the use of any groundtruth annotations. The code is made publicly available here.

New architecture GPUs like A100 are now equipped with multi-instance GPU (MIG) technology, which allows the GPU to be partitioned into multiple small, isolated instances. This technology provides more flexibility for users to support both deep learning training and inference workloads, but efficiently utilizing it can still be challenging. The vision of this paper is to provide a more comprehensive and practical benchmark study for MIG in order to eliminate the need for tedious manual benchmarking and tuning efforts. To achieve this vision, the paper presents MIGPerf, an open-source tool that streamlines the benchmark study for MIG. Using MIGPerf, the authors conduct a series of experiments, including deep learning training and inference characterization on MIG, GPU sharing characterization, and framework compatibility with MIG. The results of these experiments provide new insights and guidance for users to effectively employ MIG, and lay the foundation for further research on the orchestration of hybrid training and inference workloads on MIGs. The code and results are released on https://github.com/MLSysOps/MIGProfiler. This work is still in progress and more results will be published soon.

Tobacco origin identification is significantly important in tobacco industry. Modeling analysis for sensor data with near infrared spectroscopy has become a popular method for rapid detection of internal features. However, for sensor data analysis using traditional artificial neural network or deep network models, the training process is extremely time-consuming. In this paper, a novel broad learning system with Takagi-Sugeno (TS) fuzzy subsystem is proposed for rapid identification of tobacco origin. Incremental learning is employed in the proposed method, which obtains the weight matrix of the network after a very small amount of computation, resulting in much shorter training time for the model, with only about 3 seconds for the extra step training. The experimental results show that the TS fuzzy subsystem can extract features from the near infrared data and effectively improve the recognition performance. The proposed method can achieve the highest prediction accuracy (95.59 %) in comparison to the traditional classification algorithms, artificial neural network, and deep convolutional neural network, and has a great advantage in the training time with only about 128 seconds.

Accurate modeling of ship performance is crucial for the shipping industry to optimize fuel consumption and subsequently reduce emissions. However, predicting the speed-power relation in real-world conditions remains a challenge. In this study, we used in-service monitoring data from multiple vessels with different hull shapes to compare the accuracy of data-driven machine learning (ML) algorithms to traditional methods for assessing ship performance. Our analysis consists of two main parts: (1) a comparison of sea trial curves with calm-water curves fitted on operational data, and (2) a benchmark of multiple added wave resistance theories with an ML-based approach. Our results showed that a simple neural network outperformed established semi-empirical formulas following first principles. The neural network only required operational data as input, while the traditional methods required extensive ship particulars that are often unavailable. These findings suggest that data-driven algorithms may be more effective for predicting ship performance in practical applications.

As a common appearance defect of concrete bridges, cracks are important indices for bridge structure health assessment. Although there has been much research on crack identification, research on the evolution mechanism of bridge cracks is still far from practical applications. In this paper, the state-of-the-art research on intelligent theories and methodologies for intelligent feature extraction, data fusion and crack detection based on data-driven approaches is comprehensively reviewed. The research is discussed from three aspects: the feature extraction level of the multimodal parameters of bridge cracks, the description level and the diagnosis level of the bridge crack damage states. We focus on previous research concerning the quantitative characterization problems of multimodal parameters of bridge cracks and their implementation in crack identification, while highlighting some of their major drawbacks. In addition, the current challenges and potential future research directions are discussed.

Two approaches to AI, neural networks and symbolic systems, have been proven very successful for an array of AI problems. However, neither has been able to achieve the general reasoning ability required for human-like intelligence. It has been argued that this is due to inherent weaknesses in each approach. Luckily, these weaknesses appear to be complementary, with symbolic systems being adept at the kinds of things neural networks have trouble with and vice-versa. The field of neural-symbolic AI attempts to exploit this asymmetry by combining neural networks and symbolic AI into integrated systems. Often this has been done by encoding symbolic knowledge into neural networks. Unfortunately, although many different methods for this have been proposed, there is no common definition of an encoding to compare them. We seek to rectify this problem by introducing a semantic framework for neural-symbolic AI, which is then shown to be general enough to account for a large family of neural-symbolic systems. We provide a number of examples and proofs of the application of the framework to the neural encoding of various forms of knowledge representation and neural network. These, at first sight disparate approaches, are all shown to fall within the framework's formal definition of what we call semantic encoding for neural-symbolic AI.

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing artifacts in adverse conditions. In comparison, in such difficult scenarios, predictive models typically do not produce such artifacts but tend to distort the target speech instead, thereby degrading the speech quality. In this work, we present a stochastic regeneration approach where an estimate given by a predictive model is provided as a guide for further diffusion. We show that the proposed approach uses the predictive model to remove the vocalizing and breathing artifacts while producing very high quality samples thanks to the diffusion model, even in adverse conditions. We further show that this approach enables to use lighter sampling schemes with fewer diffusion steps without sacrificing quality, thus lifting the computational burden by an order of magnitude. Source code and audio examples are available online (https://uhh.de/inf-sp-storm).