本文调查了一种捍卫对抗性攻击的方法家族,其成功的部分原因是创造了嘈杂,不连续或不足的损失景观,而对手很难驾驶。实现这种效果的一种常见但不是普遍的方法是使用随机神经网络。我们表明,这是梯度混淆的一种形式,并根据Weierstrass变换提出了对基于梯度的对手的一般扩展,该变换平滑了损失函数的表面并提供了更可靠的梯度估计。我们进一步表明,相同的原则可以增强无梯度的对手。我们证明了消失方法对由于这种混淆而表现出鲁棒性的随机和非传统对抗防御的功效。此外,我们将分析它与对转型的期望相互作用。目前用于攻击随机防御的流行梯度采样方法。
translated by 谷歌翻译
在给定的学习任务中提供不向导会传达出一个关键的归纳偏见,如果正确指定,可以导致样本效率学习和良好的概括。但是,对于许多感兴趣的问题来说,理想的不变性通常是未知的,这既导致了工程知识,又试图为不变性学习提供框架。但是,不变性学习是昂贵的,并且对于流行的神经体系结构而言是密集的。我们介绍了摊销不变性学习的概念。在前期学习阶段,我们学习了跨越不变性的特征提取器的低维流形,该曲线跨越了不变性,可以使用超网络进行不同的转换。然后,对于任何感兴趣的问题,模型和不变性学习都可以通过拟合低维不变性描述符和输出头的速度快速有效。从经验上讲,该框架可以在不同的下游任务中识别适当的不向导,并与常规方法相比,导致可比或更好的测试性能。我们的Hyper Invariance框架在理论上也很吸引人,因为它可以实现概括性结合,从而在模型拟合和复杂性之间的权衡中提供了一个有趣的新工作点。
translated by 谷歌翻译
尽管深度神经网络能够在各种任务上实现优于人类的表现,但他们臭名昭著,因为他们需要大量的数据和计算资源,将其成功限制在可用的这些资源的领域。金属学习方法可以通过从相关任务中转移知识来解决此问题,从而减少学习新任务所需的数据和计算资源的数量。我们组织了元数据竞赛系列,该系列为世界各地的研究小组提供了创建和实验评估实际问题的新元学习解决方案的机会。在本文中,我们在竞争组织者和排名最高的参与者之间进行了合作,我们描述了竞争的设计,数据集,最佳实验结果以及Neurips 2021挑战中最高的方法,这些方法吸引了15进入最后阶段的活跃团队(通过表现优于基线),在反馈阶段进行了100多次代码提交。顶级参与者的解决方案是开源的。汲取的经验教训包括学习良好的表示对于有效的转移学习至关重要。
translated by 谷歌翻译
自我监督的学习是一个强大的范例,用于在未标记的图像上学习。基于实例匹配的大量有效的新方法依赖于数据增强来推动学习,这些方法达成了优化流行识别基准的增强方案的粗略协议。但是,有强有力的理由可疑计算机视觉中的不同任务需要对不同(IN)差异进行编码的功能,因此可能需要不同的增强策略。在本文中,我们衡量了对比方法学到的修正学知识,并确认他们确实学会了与使用的增强的不变性,进一步表明,这一不变性大大转移到与姿势和照明的相关真实变化的变化很大程度上转移。我们展示了学习的InorRARCES强烈影响下游任务性能,并确认不同的下游任务从极性相反(IN)差异中受益,导致使用标准增强策略时的性能损失。最后,我们证明,具有互补的修正条件的表现简单融合可确保对所考虑的所有不同下游任务进行广泛的可转换性。
translated by 谷歌翻译
Self-supervised visual representation learning has seen huge progress recently, but no large scale evaluation has compared the many models now available. We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction. We compare their performance to a supervised baseline and show that on most tasks the best self-supervised models outperform supervision, confirming the recently observed trend in the literature. We find ImageNet Top-1 accuracy to be highly correlated with transfer to many-shot recognition, but increasingly less so for few-shot, object detection and dense prediction. No single self-supervised method dominates overall, suggesting that universal pre-training is still unsolved. Our analysis of features suggests that top self-supervised learners fail to preserve colour information as well as supervised alternatives, but tend to induce better classifier calibration, and less attentive overfitting than supervised learners.
translated by 谷歌翻译
We introduce a novel framework to track multiple objects in overhead camera videos for airport checkpoint security scenarios where targets correspond to passengers and their baggage items. We propose a Self-Supervised Learning (SSL) technique to provide the model information about instance segmentation uncertainty from overhead images. Our SSL approach improves object detection by employing a test-time data augmentation and a regression-based, rotation-invariant pseudo-label refinement technique. Our pseudo-label generation method provides multiple geometrically-transformed images as inputs to a Convolutional Neural Network (CNN), regresses the augmented detections generated by the network to reduce localization errors, and then clusters them using the mean-shift algorithm. The self-supervised detector model is used in a single-camera tracking algorithm to generate temporal identifiers for the targets. Our method also incorporates a multi-view trajectory association mechanism to maintain consistent temporal identifiers as passengers travel across camera views. An evaluation of detection, tracking, and association performances on videos obtained from multiple overhead cameras in a realistic airport checkpoint environment demonstrates the effectiveness of the proposed approach. Our results show that self-supervision improves object detection accuracy by up to $42\%$ without increasing the inference time of the model. Our multi-camera association method achieves up to $89\%$ multi-object tracking accuracy with an average computation time of less than $15$ ms.
translated by 谷歌翻译
The availability of frequent and cost-free satellite images is in growing demand in the research world. Such satellite constellations as Landsat 8 and Sentinel-2 provide a massive amount of valuable data daily. However, the discrepancy in the sensors' characteristics of these satellites makes it senseless to use a segmentation model trained on either dataset and applied to another, which is why domain adaptation techniques have recently become an active research area in remote sensing. In this paper, an experiment of domain adaptation through style-transferring is conducted using the HRSemI2I model to narrow the sensor discrepancy between Landsat 8 and Sentinel-2. This paper's main contribution is analyzing the expediency of that approach by comparing the results of segmentation using domain-adapted images with those without adaptation. The HRSemI2I model, adjusted to work with 6-band imagery, shows significant intersection-over-union performance improvement for both mean and per class metrics. A second contribution is providing different schemes of generalization between two label schemes - NALCMS 2015 and CORINE. The first scheme is standardization through higher-level land cover classes, and the second is through harmonization validation in the field.
translated by 谷歌翻译
When a human communicates with a machine using natural language on the web and online, how can it understand the human's intention and semantic context of their talk? This is an important AI task as it enables the machine to construct a sensible answer or perform a useful action for the human. Meaning is represented at the sentence level, identification of which is known as intent detection, and at the word level, a labelling task called slot filling. This dual-level joint task requires innovative thinking about natural language and deep learning network design, and as a result, many approaches and models have been proposed and applied. This tutorial will discuss how the joint task is set up and introduce Spoken Language Understanding/Natural Language Understanding (SLU/NLU) with Deep Learning techniques. We will cover the datasets, experiments and metrics used in the field. We will describe how the machine uses the latest NLP and Deep Learning techniques to address the joint task, including recurrent and attention-based Transformer networks and pre-trained models (e.g. BERT). We will then look in detail at a network that allows the two levels of the task, intent classification and slot filling, to interact to boost performance explicitly. We will do a code demonstration of a Python notebook for this model and attendees will have an opportunity to watch coding demo tasks on this joint NLU to further their understanding.
translated by 谷歌翻译
Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed two shortcomings: illogical synthetic SQL queries from independent column sampling and arbitrary table joins. To address these issues, we propose a novel synthesis framework that incorporates key relationships from schema, imposes strong typing, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated natural language questions. When existing powerful semantic parsers are pre-finetuned on our high-quality synthesized data, our experiments show that these models have significant accuracy boosts on popular benchmarks, including new state-of-the-art performance on Spider.
translated by 谷歌翻译
Datacenter operators ensure fair and regular server maintenance by using automated processes to schedule maintenance jobs to complete within a strict time budget. Automating this scheduling problem is challenging because maintenance job duration varies based on both job type and hardware. While it is tempting to use prior machine learning techniques for predicting job duration, we find that the structure of the maintenance job scheduling problem creates a unique challenge. In particular, we show that prior machine learning methods that produce the lowest error predictions do not produce the best scheduling outcomes due to asymmetric costs. Specifically, underpredicting maintenance job duration has results in more servers being taken offline and longer server downtime than overpredicting maintenance job duration. The system cost of underprediction is much larger than that of overprediction. We present Acela, a machine learning system for predicting maintenance job duration, which uses quantile regression to bias duration predictions toward overprediction. We integrate Acela into a maintenance job scheduler and evaluate it on datasets from large-scale, production datacenters. Compared to machine learning based predictors from prior work, Acela reduces the number of servers that are taken offline by 1.87-4.28X, and reduces the server offline time by 1.40-2.80X.
translated by 谷歌翻译