自我监督的学习是一个有希望的无监督学习框架,实现了大型浮点网络取得成功。但这种网络不易部署到边缘设备。为了加速模型部署模型,在为各种下游任务中学习这种资源有限的设备的益处,我们向使用移动目标网络的二进制网络提出了一种自我监督的学习方法。特别是,我们建议共同列车,随机初始化的分类器,附加到预用浮点特征提取器,具有二进制网络。此外,我们提出了一种特征相似性损失,动态丢失平衡和改进的多级训练,以进一步提高准确性,并呼叫我们的方法燃烧。我们使用七个数据集的五个下游任务的经验验证显示,烧伤优于二进制网络的自我监督基线,有时优于预测预测。
translated by 谷歌翻译
随着自我监督学习(SSL)的成功,它已成为一种主流范式,可以从自我监督预定的预计模型中进行微调以提高下游任务的性能。但是,我们发现当前的SSL模型在执行低位量化时遭受严重的准确性下降,禁止其在资源受限应用程序中的部署。在本文中,我们提出了一种称为协同自我监督和量化学习(SSQL)的方法,以预处理量化量化的自我监督模型,从而有助于下游部署。 SSQL以自我监督的方式对比量化和完整的精度模型的特征,在每个步骤中随机选择了量化模型的位宽度。 SSQL不仅在量化较低的位宽度时显着提高了准确性,而且在大多数情况下都提高了完整精度模型的准确性。通过仅培训一次,SSQL可以同时在不同的位宽度上受益于各种下游任务。此外,在没有额外的存储开销的情况下,可以实现位宽度的灵活性,在训练和推理过程中只需要一份重量。我们理论上分析了SSQL的优化过程,并在各种基准测试中进行详尽的实验,以进一步证明我们方法的有效性。我们的代码可从https://github.com/megvii-research/ssql-eccv2022获得。
translated by 谷歌翻译
We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74.3% top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and 79.6% with a larger ResNet. We show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks. Our implementation and pretrained models are given on GitHub. 3 * Equal contribution; the order of first authors was randomly selected.
translated by 谷歌翻译
尽管最近通过剩余网络的代表学习中的自我监督方法取得了进展,但它们仍然对ImageNet分类基准进行了高度的监督学习,限制了它们在性能关键设置中的适用性。在MITROVIC等人的现有理论上洞察中建立2021年,我们提出了RELICV2,其结合了明确的不变性损失,在各种适当构造的数据视图上具有对比的目标。 Relicv2在ImageNet上实现了77.1%的前1个分类准确性,使用线性评估使用Reset50架构和80.6%,具有较大的Reset型号,优于宽边缘以前的最先进的自我监督方法。最值得注意的是,RelicV2是使用一系列标准Reset架构始终如一地始终优先于类似的对比较中的监督基线的第一个表示学习方法。最后,我们表明,尽管使用Reset编码器,Relicv2可与最先进的自我监控视觉变压器相媲美。
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
Does the dominant approach to learn representations (as a side effect of optimizing an expected cost for a single training distribution) remain a good approach when we are dealing with multiple distributions. Our thesis is that such scenarios are better served by representations that are "richer" than those obtained with a single optimization episode. This is supported by a collection of empirical results obtained with an apparently na\"ive ensembling technique: concatenating the representations obtained with multiple training episodes using the same data, model, algorithm, and hyper-parameters, but different random seeds. These independently trained networks perform similarly. Yet, in a number of scenarios involving new distributions, the concatenated representation performs substantially better than an equivalently sized network trained from scratch. This proves that the representations constructed by multiple training episodes are in fact different. Although their concatenation carries little additional information about the training task under the training distribution, it becomes substantially more informative when tasks or distributions change. Meanwhile, a single training episode is unlikely to yield such a redundant representation because the optimization process has no reason to accumulate features that do not incrementally improve the training performance.
translated by 谷歌翻译
我们通过以端到端的方式对大规模未标记的数据集进行分类,呈现扭曲,简单和理论上可解释的自我监督的表示学习方法。我们使用Softmax操作终止的暹罗网络,以产生两个增强图像的双类分布。没有监督,我们强制执行不同增强的班级分布。但是,只需最小化增强之间的分歧将导致折叠解决方案,即,输出所有图像的相同类概率分布。在这种情况下,留下有关输入图像的信息。为了解决这个问题,我们建议最大化输入和课程预测之间的互信息。具体地,我们最小化每个样品的分布的熵,使每个样品的课程预测是对每个样品自信的预测,并最大化平均分布的熵,以使不同样品的预测变得不同。以这种方式,扭曲可以自然地避免没有特定设计的折叠解决方案,例如非对称网络,停止梯度操作或动量编码器。因此,扭曲优于各种任务的最先进的方法。特别是,在半监督学习中,扭曲令人惊讶地表现出令人惊讶的是,使用Reset-50作为骨干的1%ImageNet标签实现61.2%的顶级精度,以前的最佳结果为6.2%。代码和预先训练的模型是给出的:https://github.com/byteDance/twist
translated by 谷歌翻译
当自我监督的模型已经显示出比在规模上未标记的数据训练的情况下的监督对方的可比视觉表现。然而,它们的功效在持续的学习(CL)场景中灾难性地减少,其中数据被顺序地向模型呈现给模型。在本文中,我们表明,通过添加将表示的当前状态映射到其过去状态,可以通过添加预测的网络来无缝地转换为CL的蒸馏机制。这使我们能够制定一个持续自我监督的视觉表示的框架,学习(i)显着提高了学习象征的质量,(ii)与若干最先进的自我监督目标兼容(III)几乎没有近似参数调整。我们通过在各种CL设置中培训六种受欢迎的自我监督模型来证明我们的方法的有效性。
translated by 谷歌翻译
Computational pathology can lead to saving human lives, but models are annotation hungry and pathology images are notoriously expensive to annotate. Self-supervised learning has shown to be an effective method for utilizing unlabeled data, and its application to pathology could greatly benefit its downstream tasks. Yet, there are no principled studies that compare SSL methods and discuss how to adapt them for pathology. To address this need, we execute the largest-scale study of SSL pre-training on pathology image data, to date. Our study is conducted using 4 representative SSL methods on diverse downstream tasks. We establish that large-scale domain-aligned pre-training in pathology consistently out-performs ImageNet pre-training in standard SSL settings such as linear and fine-tuning evaluations, as well as in low-label regimes. Moreover, we propose a set of domain-specific techniques that we experimentally show leads to a performance boost. Lastly, for the first time, we apply SSL to the challenging task of nuclei instance segmentation and show large and consistent performance improvements under diverse settings.
translated by 谷歌翻译
我们研究了用于半监控学习(SSL)的无监督数据选择,其中可以提供大规模的未标记数据集,并且为标签采集预算小额数据子集。现有的SSL方法专注于学习一个有效地集成了来自给定小标记数据和大型未标记数据的信息的模型,而我们专注于选择正确的数据以用于SSL的注释,而无需任何标签或任务信息。直观地,要标记的实例应统称为下游任务的最大多样性和覆盖范围,并且单独具有用于SSL的最大信息传播实用程序。我们以三步数据为中心的SSL方法形式化这些概念,使稳定性和精度的纤维液改善8%的CiFar-10(标记为0.08%)和14%的Imagenet -1k(标记为0.2%)。它也是一种具有各种SSL方法的通用框架,提供一致的性能增益。我们的工作表明,在仔细选择注释数据上花费的小计算带来了大注释效率和模型性能增益,而无需改变学习管道。我们完全无监督的数据选择可以轻松扩展到其他弱监督的学习设置。
translated by 谷歌翻译
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or "views") of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a "swapped" prediction mechanism where we predict the code of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements. We validate our findings by achieving 75.3% top-1 accuracy on ImageNet with ResNet-50, as well as surpassing supervised pretraining on all the considered transfer tasks.
translated by 谷歌翻译
近年来,基于对比的自我监督学习方法取得了巨大的成功。但是,自学要求非常长的训练时期(例如,MoCO V3的800个时代)才能获得有希望的结果,这对于一般学术界来说是不可接受的,并阻碍了该主题的发展。这项工作重新审视了基于动量的对比学习框架,并确定了两种增强观点仅产生一个积极对的效率低下。我们提出了快速MOCO-一个新颖的框架,该框架利用组合贴片从两个增强视图中构造了多对正面,该视图提供了丰富的监督信号,这些信号带来了可忽视的额外计算成本,从而带来了显着的加速。经过100个时期训练的快速MOCO实现了73.5%的线性评估精度,类似于经过800个时期训练的MOCO V3(Resnet-50骨干)。额外的训练(200个时期)进一步将结果提高到75.1%,这与最先进的方法相当。几个下游任务的实验也证实了快速MOCO的有效性。
translated by 谷歌翻译
我们专注于更好地理解增强不变代表性学习的关键因素。我们重新访问moco v2和byol,并试图证明以下假设的真实性:不同的框架即使具有相同的借口任务也会带来不同特征的表示。我们建立了MoCo V2和BYOL之间公平比较的第一个基准,并观察:(i)复杂的模型配置使得可以更好地适应预训练数据集; (ii)从实现竞争性转移表演中获得的预训练和微调阻碍模型的优化策略不匹配。鉴于公平的基准,我们进行进一步的研究并发现网络结构的不对称性赋予对比框架在线性评估协议下正常工作,同时可能会损害长尾分类任务的转移性能。此外,负样本并不能使模型更明智地选择数据增强,也不会使不对称网络结构结构。我们相信我们的发现为将来的工作提供了有用的信息。
translated by 谷歌翻译
我们提出了一种适用于半全球任务的自学学习(SSL)方法,例如对象检测和语义分割。我们通过在训练过程中最大程度地减少像素级局部对比度(LC)损失,代表了同一图像转换版本的相应图像位置之间的局部一致性。可以将LC-LOSS添加到以最小开销的现有自我监督学习方法中。我们使用可可,Pascal VOC和CityScapes数据集评估了两个下游任务的SSL方法 - 对象检测和语义细分。我们的方法的表现优于现有的最新SSL方法可可对象检测的方法1.9%,Pascal VOC检测1.4%,而CityScapes Sementation则为0.6%。
translated by 谷歌翻译
许多最近的自我监督学习方法在图像分类和其他任务上表现出了令人印象深刻的表现。已经使用了一种令人困惑的多种技术,并不总是清楚地了解其收益的原因,尤其是在组合使用时。在这里,我们将图像的嵌入视为点粒子,并将模型优化视为该粒子系统上的动态过程。我们的动态模型结合了类似图像的吸引力,避免局部崩溃的局部分散力以及实现颗粒的全球均匀分布的全局分散力。动态透视图突出了使用延迟参数图像嵌入(a la byol)以及同一图像的多个视图的优点。它还使用纯动态的局部分散力(布朗运动),该分散力比其他方法显示出改善的性能,并且不需要其他粒子坐标的知识。该方法称为MSBREG,代表(i)多视质心损失,它施加了吸引力的力来将不同的图像视图嵌入到其质心上,(ii)奇异值损失,将粒子系统推向空间均匀的密度( iii)布朗扩散损失。我们评估MSBREG在ImageNet上的下游分类性能以及转移学习任务,包括细粒度分类,多类对象分类,对象检测和实例分段。此外,我们还表明,将我们的正则化术语应用于其他方法,进一步改善了其性能并通过防止模式崩溃来稳定训练。
translated by 谷歌翻译
通过自学学习的视觉表示是一项极具挑战性的任务,因为网络需要在没有监督提供的主动指导的情况下筛选出相关模式。这是通过大量数据增强,大规模数据集和过量量的计算来实现的。视频自我监督学习(SSL)面临着额外的挑战:视频数据集通常不如图像数据集那么大,计算是一个数量级,并且优化器所必须通过的伪造模式数量乘以几倍。因此,直接从视频数据中学习自我监督的表示可能会导致次优性能。为了解决这个问题,我们建议在视频表示学习框架中利用一个以自我或语言监督为基础的强大模型,并在不依赖视频标记的数据的情况下学习强大的空间和时间信息。为此,我们修改了典型的基于视频的SSL设计和目标,以鼓励视频编码器\ textit {subsume}基于图像模型的语义内容,该模型在通用域上训练。所提出的算法被证明可以更有效地学习(即在较小的时期和较小的批次中),并在单模式SSL方法中对标准下游任务进行了新的最新性能。
translated by 谷歌翻译
Deep transfer learning has been widely used for knowledge transmission in recent years. The standard approach of pre-training and subsequently fine-tuning, or linear probing, has shown itself to be effective in many down-stream tasks. Therefore, a challenging and ongoing question arises: how to quantify cross-task transferability that is compatible with transferred results while keeping self-consistency? Existing transferability metrics are estimated on the particular model by conversing source and target tasks. They must be recalculated with all existing source tasks whenever a novel unknown target task is encountered, which is extremely computationally expensive. In this work, we highlight what properties should be satisfied and evaluate existing metrics in light of these characteristics. Building upon this, we propose Principal Gradient Expectation (PGE), a simple yet effective method for assessing transferability across tasks. Specifically, we use a restart scheme to calculate every batch gradient over each weight unit more than once, and then we take the average of all the gradients to get the expectation. Thus, the transferability between the source and target task is estimated by computing the distance of normalized principal gradients. Extensive experiments show that the proposed transferability metric is more stable, reliable and efficient than SOTA methods.
translated by 谷歌翻译
自我监督学习(SSL)已取得了有希望的下游表现。但是,当面临现实世界应用程序中的各种资源预算时,将一一一个尺寸的多个网络预算到多个网络的巨大计算负担。在本文中,我们提出了基于歧视性SSL的可靠预处理网络(DSPNET),可以立即训练,然后缩小到各种大小的多个子网络,每个尺寸都可以忠实地学习良好的表示,并可以作为良好的初始化,以良好的初始化。具有各种资源预算的下游任务。具体而言,我们通过优雅地集成SSL和知识蒸馏,将微小网络的思想扩展到判别性SSL范式。我们在图像网上与网络与线性评估和半监督评估方案的一个单独预处理的网络表现出可比性或改进的性能,同时降低了较大的培训成本。预处理的模型还可以很好地推广到下游检测和分割任务。代码将公开。
translated by 谷歌翻译
特征回归是将大型神经网络模型蒸馏到较小的功能回归。我们表明,随着网络架构的简单变化,回归可能会优于自我监督模型的知识蒸馏更复杂的最先进方法。令人惊讶的是,即使仅在蒸馏过程中仅使用并且在下游任务中丢弃时,将多层的Perceptron头部添加到CNN骨架上是有益的。因此,更深的非线性投影可以使用在不改变推理架构和时间的情况下准确地模仿老师。此外,我们利用独立的投影头来同时蒸馏多个教师网络。我们还发现,使用与教师和学生网络的输入相同的弱增强图像辅助蒸馏。Imagenet DataSet上的实验证明了各种自我监督蒸馏环境中提出的变化的功效。
translated by 谷歌翻译