培训视频中人类姿势估计的最先进模型需要具有很难获得的注释的数据集。尽管最近已将变压器用于身体姿势序列建模，但相关方法依靠伪地真相来增强目前有限的培训数据可用于学习此类模型。在本文中，我们介绍了Posebert，Posebert是一个通过掩盖建模对3D运动捕获（MOCAP）数据进行全面训练的变压器模块。它是简单，通用和通用的，因为它可以插入任何基于图像的模型的顶部，以在基于视频的模型中使用时间信息。我们展示了Posebert的变体，不同的输入从3D骨骼关键点到全身或仅仅是手（Mano）的3D参数模型的旋转。由于Posebert培训是任务不可知论的，因此该模型可以应用于姿势细化，未来的姿势预测或运动完成等几个任务。我们的实验结果验证了在各种最新姿势估计方法之上添加Posebert始终提高其性能，而其低计算成本使我们能够在实时演示中使用它，以通过A的机器人手使机器人手通过摄像头。可以在https://github.com/naver/posebert上获得测试代码和型号。

Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images apart, one can train highly transferable visual representations. As revealed by recent studies, heavy data augmentation and large sets of negatives are both crucial in learning such representations. At the same time, data mixing strategies, either at the image or the feature level, improve both supervised and semi-supervised learning by synthesizing novel examples, forcing networks to learn more robust features. In this paper, we argue that an important aspect of contrastive learning, i.e. the effect of hard negatives, has so far been neglected. To get more meaningful negative samples, current top contrastive self-supervised learning approaches either substantially increase the batch sizes, or keep very large memory banks; increasing memory requirements, however, leads to diminishing returns in terms of performance. We therefore start by delving deeper into a top-performing framework and show evidence that harder negatives are needed to facilitate better and faster learning. Based on these observations, and motivated by the success of data mixing, we propose hard negative mixing strategies at the feature level, that can be computed on-the-fly with a minimal computational overhead. We exhaustively ablate our approach on linear classification, object detection, and instance segmentation and show that employing our hard negative mixing procedure improves the quality of visual representations learned by a state-of-the-art self-supervised learning method.Project page: https://europe.naverlabs.com/mochi 34th Conference on Neural Information Processing Systems (NeurIPS 2020),

Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics. As in other fields of deep learning, tools have been devised to extract features such as sequence motifs that can explain the predictions made by a trained network. Here we intend to go beyond explainable machine learning and introduce SEISM, a selective inference procedure to test the association between these extracted features and the predicted phenotype. In particular, we discuss how training a one-layer convolutional network is formally equivalent to selecting motifs maximizing some association score. We adapt existing sampling-based selective inference procedures by quantizing this selection over an infinite set to a large but finite grid. Finally, we show that sampling under a specific choice of parameters is sufficient to characterize the composite null hypothesis typically used for selective inference-a result that goes well beyond our particular framework. We illustrate the behavior of our method in terms of calibration, power and speed and discuss its power/speed trade-off with a simpler data-split strategy. SEISM paves the way to an easier analysis of neural networks used in regulatory genomics, and to more powerful methods for genome wide association studies (GWAS).

In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10 - 20 meters) is arguably needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map over the "Landes de Gascogne" forest in France, a large maritime pine plantation of 13,000 km$^2$ with flat terrain and intensive management. This area is characterized by even-aged and mono-specific stands, of a typical length of a few hundred meters, harvested every 35 to 50 years. Our deep learning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 with composite time averages as input to predict tree height derived from GEDI waveforms. The evaluation is performed with external validation data from forest inventory plots and a stereo 3D reconstruction model based on Skysat imagery available at specific locations. We trained seven different U-net models based on a combination of Sentinel-1 and Sentinel-2 bands to evaluate the importance of each instrument in the dominant height retrieval. The model outputs allow us to generate a 10 m resolution canopy height map of the whole "Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 m on the Test dataset. The best predictions were obtained using all available satellite layers from Sentinel-1 and Sentinel-2 but using only one satellite source also provided good predictions. For all validation datasets in coniferous forests, our model showed better metrics than previous canopy height models available in the same region.

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher model for every new dataset. Alternatively, one may directly work on the improvement of the optimization procedure of the compact model toward better generalization. Recent works observe that the flatness of the local minimum correlates well with better generalization. In this work, we adapt Stochastic Weight Averaging (SWA), a method encouraging convergence to a flatter minimum, to fine-tuning PLMs. We conduct extensive experiments on various NLP tasks (text classification, question answering, and generation) and different model architectures and demonstrate that our adaptation improves the generalization without extra computation cost. Moreover, we observe that this simple optimization technique is able to outperform the state-of-the-art KD methods for compact models.

This work addresses the problems of (a) designing utilization measurements of trained artificial intelligence (AI) models and (b) explaining how training data are encoded in AI models based on those measurements. The problems are motivated by the lack of explainability of AI models in security and safety critical applications, such as the use of AI models for classification of traffic signs in self-driving cars. We approach the problems by introducing theoretical underpinnings of AI model utilization measurement and understanding patterns in utilization-based class encodings of traffic signs at the level of computation graphs (AI models), subgraphs, and graph nodes. Conceptually, utilization is defined at each graph node (computation unit) of an AI model based on the number and distribution of unique outputs in the space of all possible outputs (tensor-states). In this work, utilization measurements are extracted from AI models, which include poisoned and clean AI models. In contrast to clean AI models, the poisoned AI models were trained with traffic sign images containing systematic, physically realizable, traffic sign modifications (i.e., triggers) to change a correct class label to another label in a presence of such a trigger. We analyze class encodings of such clean and poisoned AI models, and conclude with implications for trojan injection and detection.

White matter bundle segmentation is a cornerstone of modern tractography to study the brain's structural connectivity in domains such as neurological disorders, neurosurgery, and aging. In this study, we present FIESTA (FIber gEneration and bundle Segmentation in Tractography using Autoencoders), a reliable and robust, fully automated, and easily semi-automatically calibrated pipeline based on deep autoencoders that can dissect and fully populate WM bundles. Our framework allows the transition from one anatomical bundle definition to another with marginal calibrating time. This pipeline is built upon FINTA, CINTA, and GESTA methods that demonstrated how autoencoders can be used successfully for streamline filtering, bundling, and streamline generation in tractography. Our proposed method improves bundling coverage by recovering hard-to-track bundles with generative sampling through the latent space seeding of the subject bundle and the atlas bundle. A latent space of streamlines is learned using autoencoder-based modeling combined with contrastive learning. Using an atlas of bundles in standard space (MNI), our proposed method segments new tractograms using the autoencoder latent distance between each tractogram streamline and its closest neighbor bundle in the atlas of bundles. Intra-subject bundle reliability is improved by recovering hard-to-track streamlines, using the autoencoder to generate new streamlines that increase each bundle's spatial coverage while remaining anatomically meaningful. Results show that our method is more reliable than state-of-the-art automated virtual dissection methods such as RecoBundles, RecoBundlesX, TractSeg, White Matter Analysis and XTRACT. Overall, these results show that our framework improves the practicality and usability of current state-of-the-art bundling framework

There are many potential benefits to news readers accessing diverse sources. Modern news aggregators do the hard work of organizing the news, offering readers a plethora of source options, but choosing which source to read remains challenging. We propose a new framework to assist readers in identifying source differences and gaining an understanding of news coverage diversity. The framework is based on the generation of Discord Questions: questions with a diverse answer pool, explicitly illustrating source differences. To assemble a prototype of the framework, we focus on two components: (1) discord question generation, the task of generating questions answered differently by sources, for which we propose an automatic scoring method, and create a model that improves performance from current question generation (QG) methods by 5%, (2) answer consolidation, the task of grouping answers to a question that are semantically similar, for which we collect data and repurpose a method that achieves 81% balanced accuracy on our realistic test set. We illustrate the framework's feasibility through a prototype interface. Even though model performance at discord QG still lags human performance by more than 15%, generated questions are judged to be more interesting than factoid questions and can reveal differences in the level of detail, sentiment, and reasoning of sources in news coverage.

In a fissile material, the inherent multiplicity of neutrons born through induced fissions leads to correlations in their detection statistics. The correlations between neutrons can be used to trace back some characteristics of the fissile material. This technique known as neutron noise analysis has applications in nuclear safeguards or waste identification. It provides a non-destructive examination method for an unknown fissile material. This is an example of an inverse problem where the cause is inferred from observations of the consequences. However, neutron correlation measurements are often noisy because of the stochastic nature of the underlying processes. This makes the resolution of the inverse problem more complex since the measurements are strongly dependent on the material characteristics. A minor change in the material properties can lead to very different outputs. Such an inverse problem is said to be ill-posed. For an ill-posed inverse problem the inverse uncertainty quantification is crucial. Indeed, seemingly low noise in the data can lead to strong uncertainties in the estimation of the material properties. Moreover, the analytical framework commonly used to describe neutron correlations relies on strong physical assumptions and is thus inherently biased. This paper addresses dual goals. Firstly, surrogate models are used to improve neutron correlations predictions and quantify the errors on those predictions. Then, the inverse uncertainty quantification is performed to include the impact of measurement error alongside the residual model bias.

In this research work, we have demonstrated the application of Mask-RCNN (Regional Convolutional Neural Network), a deep-learning algorithm for computer vision and specifically object detection, to semiconductor defect inspection domain. Stochastic defect detection and classification during semiconductor manufacturing has grown to be a challenging task as we continuously shrink circuit pattern dimensions (e.g., for pitches less than 32 nm). Defect inspection and analysis by state-of-the-art optical and e-beam inspection tools is generally driven by some rule-based techniques, which in turn often causes to misclassification and thereby necessitating human expert intervention. In this work, we have revisited and extended our previous deep learning-based defect classification and detection method towards improved defect instance segmentation in SEM images with precise extent of defect as well as generating a mask for each defect category/instance. This also enables to extract and calibrate each segmented mask and quantify the pixels that make up each mask, which in turn enables us to count each categorical defect instances as well as to calculate the surface area in terms of pixels. We are aiming at detecting and segmenting different types of inter-class stochastic defect patterns such as bridge, break, and line collapse as well as to differentiate accurately between intra-class multi-categorical defect bridge scenarios (as thin/single/multi-line/horizontal/non-horizontal) for aggressive pitches as well as thin resists (High NA applications). Our proposed approach demonstrates its effectiveness both quantitatively and qualitatively.