Evaluating neural network performance is critical to deep neural network design but a costly procedure. Neural predictors provide an efficient solution by treating architectures as samples and learning to estimate their performance on a given task. However, existing predictors are task-dependent, predominantly estimating neural network performance on image classification benchmarks. They are also search-space dependent; each predictor is designed to make predictions for a specific architecture search space with predefined topologies and set of operations. In this paper, we propose a novel All-in-One Predictor (AIO-P), which aims to pretrain neural predictors on architecture examples from multiple, separate computer vision (CV) task domains and multiple architecture spaces, and then transfer to unseen downstream CV tasks or neural architectures. We describe our proposed techniques for general graph representation, efficient predictor pretraining and knowledge infusion techniques, as well as methods to transfer to downstream tasks/spaces. Extensive experimental results show that AIO-P can achieve Mean Absolute Error (MAE) and Spearman's Rank Correlation (SRCC) below 1% and above 0.5, respectively, on a breadth of target downstream CV tasks with or without fine-tuning, outperforming a number of baselines. Moreover, AIO-P can directly transfer to new architectures not seen during training, accurately rank them and serve as an effective performance estimator when paired with an algorithm designed to preserve performance while reducing FLOPs.
translated by 谷歌翻译
Predicting neural architecture performance is a challenging task and is crucial to neural architecture design and search. Existing approaches either rely on neural performance predictors which are limited to modeling architectures in a predefined design space involving specific sets of operators and connection rules, and cannot generalize to unseen architectures, or resort to zero-cost proxies which are not always accurate. In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble. Specifically, GENNAPE represents a given neural network as a Computation Graph (CG) of atomic operations which can model an arbitrary architecture. It first learns a graph encoder via Contrastive Learning to encourage network separation by topological features, and then trains multiple predictor heads, which are soft-aggregated according to the fuzzy membership of a neural network. Experiments show that GENNAPE pretrained on NAS-Bench-101 can achieve superior transferability to 5 different public neural network benchmarks, including NAS-Bench-201, NAS-Bench-301, MobileNet and ResNet families under no or minimum fine-tuning. We further introduce 3 challenging newly labelled neural network benchmarks: HiAML, Inception and Two-Path, which can concentrate in narrow accuracy ranges. Extensive experiments show that GENNAPE can correctly discern high-performance architectures in these families. Finally, when paired with a search algorithm, GENNAPE can find architectures that improve accuracy while reducing FLOPs on three families.
translated by 谷歌翻译
在本文中,我们将$ \ textit {开放设定识别} $与域移动一起研究,最终目标是实现$ \ textit {无源的通用域apation} $(sf-unda),以解决以下情况源和目标域之间存在域和类别变化。在SF-UNDA设置下,该模型在目标适应过程中无法再访问源数据,旨在解决数据隐私问题。我们提出了一种新颖的培训计划,以学习($ n $+1) - 道路分类器,以预测$ n $源类和未知类别,其中仅可用于培训的样本。此外,对于目标适应,我们简单地采用了加权熵最小化,以使源预处理的模型适应未标记的目标域而没有源数据。在实验中,我们显示了:$ \ textbf {1)} $在源培训后,生成的源模型可以获得$ \ textit {开放设定单域概括} $以及$ \ textit {开放设定{open-Set识别}的出色性能$任务; $ \ textbf {2)} $在目标适应后,我们的方法超过了当前的UNDA方法,这些方法在几个基准上的适应过程中需要源数据。对几个不同任务的多功能性强烈证明了我们方法的功效和概括能力。 $ \ textbf {3)} $在目标适应过程中使用封闭设置的域适应方法增强时,我们的无源方法进一步超过了当前的最新unda方法,将当前的方法提高2.5%,7.2%和13% Office-31,办公室和Visda。代码将在https://github.com/albert0147/onering中提供。
translated by 谷歌翻译
域适应(DA)旨在缓解源域和目标域之间的域移位。大多数DA方法都需要访问源数据,但通常是不可能的(例如,由于数据隐私或知识产权)。在本文中,我们解决了挑战的无源域适应(SFDA)问题,其中源净定模型在没有源数据的情况下适应目标域。我们的方法基于目标数据的观察,该数据可能不再与源域分类器对齐,仍然形成清晰的群集。我们通过定义目标数据的本地亲和力来捕获此内在结构,并鼓励具有高局部亲和力的数据之间的标签一致性。我们观察到应将更高的亲和力分配给互惠邻居,并提出自正规化损失以减少嘈杂邻居的负面影响。此外,要使用更多上下文聚合信息,我们考虑扩展的邻域,具有小关联值。在实验结果中,我们验证了目标特征的固有结构是域适应的重要信息来源。我们证明可以通过考虑本地邻居,互易邻居和扩展的邻域来有效地捕获该局部结构。最后,我们在几个2D图像和3D点云识别数据集中实现最先进的性能。代码是在https://github.com/albert0147/sfda_neighbors中获得的。
translated by 谷歌翻译
在实际情况下,代理观察的状态观察可能含有测量误差或对抗性噪音,误导代理人在训练时采取次优行动甚至崩溃。在本文中,我们研究了分布加固学习的培训稳健性〜(RL),一类最先进的方法,即估计整个分布,而不是仅期望的总回报。首先,我们验证了基于期望和分布的Bellman运营商在状态 - Noisy Markov决策过程〜(SN-MDP)中的收缩,该典型表格案例包含随机和对抗状态观察噪声。除了SN-MDP之外,我们将分析基于期望的RL中最小二乘损失的脆弱性,具有线性或非线性函数近似。相比之下,基于直方图密度估计理论地表征分布RL损耗的有界梯度规范。由此产生的稳定梯度,而分布RL的优化占其更好地训练稳健性,而不是国家观察噪声。最后,在游戏套件上进行了广泛的实验,在不同的状态观察噪声的不同强度下,在SN-MDP样设置中验证了基于期望和分布RL的收敛性。更重要的是,与SN-MDP之外的嘈杂设置中,与基于期望的对应物相比,分布RL与嘈杂的状态观察相比,分配RL不易受到噪声的噪声。
translated by 谷歌翻译
糖尿病性视网膜病(DR)已成为工人衰老人视力障碍的主要原因之一,在全球范围内是一个严重的问题。但是,大多数作品都忽略了标签的序数信息。在这个项目中,我们提出了一种新型设计MTCSNN,这是一种多任务临床暹罗神经网络,用于糖尿病性视网膜病变严重性预测任务。该项目的新颖性是在标签之间利用序数信息并添加新的回归任务,这可以帮助模型学习更多的歧视性特征,以嵌入细粒度的分类任务。我们对视视视视视视视视视reinamnist进行了全面的实验,将MTCSNN与Resnet-18、34、50等其他模型进行了比较。我们的结果表明,MTCSNN的表现优于测试数据集中的AUC和准确性。
translated by 谷歌翻译
大多数元学习方法都假设存在于可用于基本知识的情节元学习的一组非常大的标记数据。这与更现实的持续学习范例形成对比,其中数据以包含不相交类的任务的形式逐步到达。在本文中,我们考虑了这个增量元学习(IML)的这个问题,其中类在离散任务中逐步呈现。我们提出了一种方法,我们调用了IML,我们称之为eCISODIC重播蒸馏(ERD),该方法将来自当前任务的类混合到当前任务中,当研究剧集时,来自先前任务的类别示例。然后将这些剧集用于知识蒸馏以最大限度地减少灾难性的遗忘。四个数据集的实验表明ERD超越了最先进的。特别是,在一次挑战的单次次数较挑战,长任务序列增量元学习场景中,我们将IML和联合训练与当前状态的3.5%/ 10.1%/ 13.4%之间的差距降低我们在Diered-ImageNet / Mini-ImageNet / CIFAR100上分别为2.6%/ 2.9%/ 5.0%。
translated by 谷歌翻译