最近，Diffenderfer和Kailkhura提出了一种新的范式，仅通过修剪和量化随机加权的全精度神经网络，以学习紧凑而高度准确的二进制神经网络。但是，这些多质票（MPTS）的准确性对最佳的修剪比率高度敏感，这限制了其适用性。此外，原始实施没有获得任何培训或推理速度益处。在本报告中，我们讨论了克服这些局限性的几项改进。我们通过在CIFAR-10上进行实验来展示提出的技术的好处。

提高深神经网络（DNN）对分布（OOD）数据的准确性对于在现实世界应用中接受深度学习（DL）至关重要。已经观察到，分布（ID）与OOD数据的准确性遵循线性趋势和模型表现优于该基线非常罕见（并被称为“有效鲁棒”）。最近，已经开发出一些有前途的方法来提高OOD的鲁棒性：模型修剪，数据增强和结合或零射门评估大型预审预周化模型。但是，仍然对观察有效鲁棒性所需的OOD数据和模型属性的条件尚无清晰的了解。我们通过对多种方法进行全面的经验研究来解决这个问题，这些方法已知会影响OOD鲁棒性，对CIFAR-10和Imagenet的广泛自然和合成分布转移。特别是，我们通过傅立叶镜头观察“有效的鲁棒性难题”，并询问模型和OOD数据的光谱特性如何影响相应的有效鲁棒性。我们发现这个傅立叶镜头提供了一些深入的了解，为什么某些强大的模型，尤其是夹家族的模型，可以实现稳健性。但是，我们的分析还清楚地表明，没有已知的指标始终是对OOD鲁棒性的最佳解释（甚至是强烈的解释）。因此，为了帮助未来对OOD难题的研究，我们通过引入一组预处理的模型（固定的模型），以有效的稳健性（可公开可鲁棒）解决了差距，这些模型（固有的模型）以及不同级别的OOD稳健性。

深度学习方法通​​过依靠极大的大量参数化神经网络来提供许多应用程序的最先进性能。但是，此类网络已被证明非常脆弱，并不能很好地概括为新用途案例，并且通常很难在资源有限的平台上部署。模型修剪，即减少网络的大小，是一种广泛采用的策略，可以导致更健壮和可推广的网络 - 通常较小的数量级，具有相同甚至改善的性能。尽管有许多用于修剪模型的启发式方法，但我们对修剪过程的理解仍然有限。实证研究表明，某些启发式方法可以改善性能，而另一些可以使模型更脆或具有其他副作用。这项工作旨在阐明不同的修剪方法如何改变网络的内部功能表示以及对模型性能的相应影响。为了提供模型特征空间的有意义的比较和表征，我们使用三个几何指标，这些指标是从共同采用的分类损失中分解的。使用这些指标，我们设计了一个可视化系统，以突出修剪对模型预测以及潜在功能嵌入的影响。所提出的工具为探索和研究修剪方法以及修剪和原始模型之间的差异提供了一个环境。通过利用我们的可视化，ML研究人员不仅可以识别模型修剪和数据损坏的样本，而且还可以获得有关某些修剪模型如何实现出色鲁棒性能的见解和解释。

野外的深度学习（DL）的成功采用需要模型：（1）紧凑，（2）准确，（3）强大的分布换档。不幸的是，同时满足这些要求的努力主要是不成功的。这提出了一个重要问题：无法创建紧凑，准确，强大的深神经网络（卡）基础？为了回答这个问题，我们对流行的模型压缩技术进行了大规模分析，该技术揭示了几种有趣模式。值得注意的是，与传统的修剪方法相比（例如，微调和逐渐修剪），我们发现“彩票式风格”方法令人惊讶地用于生产卡，包括二进制牌。具体而言，我们能够创建极其紧凑的卡，与其较大的对应物相比，具有类似的测试精度和匹配（或更好）的稳健性 - 仅通过修剪和（可选）量化。利用卡的紧凑性，我们开发了一种简单的域 - 自适应测试时间合并方法（卡片 - 甲板），它使用门控模块根据与测试样本的光谱相似性动态地选择相应的卡片。该拟议的方法建立了一个“赢得胜利”的卡片，即在CiFar-10-C精度（即96.8％标准和92.75％的鲁棒）和CiFar-100- C精度（80.6％标准和71.3％的稳健性），内存使用率比非压缩基线（Https://github.com/robustbench/robustbench提供的预制卡和卡片 - 甲板）。最后，我们为我们的理论支持提供了理论支持经验研究结果。

Designing experiments often requires balancing between learning about the true treatment effects and earning from allocating more samples to the superior treatment. While optimal algorithms for the Multi-Armed Bandit Problem (MABP) provide allocation policies that optimally balance learning and earning, they tend to be computationally expensive. The Gittins Index (GI) is a solution to the MABP that can simultaneously attain optimality and computationally efficiency goals, and it has been recently used in experiments with Bernoulli and Gaussian rewards. For the first time, we present a modification of the GI rule that can be used in experiments with exponentially-distributed rewards. We report its performance in simulated 2- armed and 3-armed experiments. Compared to traditional non-adaptive designs, our novel GI modified design shows operating characteristics comparable in learning (e.g. statistical power) but substantially better in earning (e.g. direct benefits). This illustrates the potential that designs using a GI approach to allocate participants have to improve participant benefits, increase efficiencies, and reduce experimental costs in adaptive multi-armed experiments with exponential rewards.

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.

Extracting complex structures from grid-based data is a common key step in automated medical image analysis. The conventional solution to recovering tree-structured geometries typically involves computing the minimal cost path through intermediate representations derived from segmentation masks. However, this methodology has significant limitations in the context of projective imaging of tree-structured 3D anatomical data such as coronary arteries, since there are often overlapping branches in the 2D projection. In this work, we propose a novel approach to predicting tree connectivity structure which reformulates the task as an optimization problem over individual steps of a recursive process. We design and train a two-stage model which leverages the UNet and Transformer architectures and introduces an image-based prompting technique. Our proposed method achieves compelling results on a pair of synthetic datasets, and outperforms a shortest-path baseline.

Cashews are grown by over 3 million smallholders in more than 40 countries worldwide as a principal source of income. As the third largest cashew producer in Africa, Benin has nearly 200,000 smallholder cashew growers contributing 15% of the country's national export earnings. However, a lack of information on where and how cashew trees grow across the country hinders decision-making that could support increased cashew production and poverty alleviation. By leveraging 2.4-m Planet Basemaps and 0.5-m aerial imagery, newly developed deep learning algorithms, and large-scale ground truth datasets, we successfully produced the first national map of cashew in Benin and characterized the expansion of cashew plantations between 2015 and 2021. In particular, we developed a SpatioTemporal Classification with Attention (STCA) model to map the distribution of cashew plantations, which can fully capture texture information from discriminative time steps during a growing season. We further developed a Clustering Augmented Self-supervised Temporal Classification (CASTC) model to distinguish high-density versus low-density cashew plantations by automatic feature extraction and optimized clustering. Results show that the STCA model has an overall accuracy of 80% and the CASTC model achieved an overall accuracy of 77.9%. We found that the cashew area in Benin has doubled from 2015 to 2021 with 60% of new plantation development coming from cropland or fallow land, while encroachment of cashew plantations into protected areas has increased by 70%. Only half of cashew plantations were high-density in 2021, suggesting high potential for intensification. Our study illustrates the power of combining high-resolution remote sensing imagery and state-of-the-art deep learning algorithms to better understand tree crops in the heterogeneous smallholder landscape.

Grasping is an incredible ability of animals using their arms and limbs in their daily life. The human hand is an especially astonishing multi-fingered tool for precise grasping, which helped humans to develop the modern world. The implementation of the human grasp to virtual reality and telerobotics is always interesting and challenging at the same time. In this work, authors surveyed, studied, and analyzed the human hand-grasping behavior for the possibilities of haptic grasping in the virtual and remote environment. This work is focused on the motion and force analysis of fingers in human hand grasping scenarios and the paper describes the transition of the human hand grasping towards a tripod haptic grasp model for effective interaction in virtual reality.

Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i.e., the forecasts should satisfy the hierarchical aggregation constraints. Moreover, the disparities of statistical characteristics between levels can be huge, worsened by non-Gaussian distributions and non-linear correlations. To this extent, we propose a novel end-to-end hierarchical time series forecasting model, based on conditioned normalizing flow-based autoregressive transformer reconciliation, to represent complex data distribution while simultaneously reconciling the forecasts to ensure coherency. Unlike other state-of-the-art methods, we achieve the forecasting and reconciliation simultaneously without requiring any explicit post-processing step. In addition, by harnessing the power of deep model, we do not rely on any assumption such as unbiased estimates or Gaussian distribution. Our evaluation experiments are conducted on four real-world hierarchical datasets from different industrial domains (three public ones and a dataset from the application servers of Alipay's data center) and the preliminary results demonstrate efficacy of our proposed method.