很少有射击学习(FSL)旨在使用有限标记的示例生成分类器。许多现有的作品采用了元学习方法,构建了一些可以从几个示例中学习以生成分类器的学习者。通常,几次学习者是通过依次对多个几次射击任务进行采样并优化几杆学习者在为这些任务生成分类器时的性能来构建或进行元训练的。性能是通过结果分类器对这些任务的测试(即查询)示例进行分类的程度来衡量的。在本文中,我们指出了这种方法的两个潜在弱点。首先,采样的查询示例可能无法提供足够的监督来进行元训练少数学习者。其次,元学习的有效性随着射击数量的增加而急剧下降。为了解决这些问题,我们为少数学习者提出了一个新颖的元训练目标,这是为了鼓励少数学习者生成像强大分类器一样执行的分类器。具体而言,我们将每个采样的几个弹药任务与强大的分类器相关联,该分类器接受了充分的标记示例。强大的分类器可以看作是目标分类器,我们希望在几乎没有示例的情况下生成的几个学习者,我们使用强大的分类器来监督少数射击学习者。我们提出了一种构建强分类器的有效方法,使我们提出的目标成为现有基于元学习的FSL方法的易于插入的术语。我们与许多代表性的元学习方法相结合验证了我们的方法,Lastshot。在几个基准数据集中,我们的方法可导致各种任务的显着改进。更重要的是,通过我们的方法,基于元学习的FSL方法可以在不同数量的镜头上胜过基于非Meta学习的方法。
translated by 谷歌翻译
The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard benchmarks in meta-learning. In this work, we show that a simple baseline: learning a supervised or selfsupervised representation on the meta-training set, followed by training a linear classifier on top of this representation, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of selfdistillation. This demonstrates that using a good learned embedding model can be more effective than sophisticated meta-learning algorithms. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.
translated by 谷歌翻译
元学习已成为几乎没有图像分类的实用方法,在该方法中,“学习分类器的策略”是在标记的基础类别上进行元学习的,并且可以应用于具有新颖类的任务。我们删除了基类标签的要求,并通过无监督的元学习(UML)学习可通用的嵌入。具体而言,任务发作是在元训练过程中使用未标记的基本类别的数据增强构建的,并且我们将基于嵌入式的分类器应用于新的任务,并在元测试期间使用标记的少量示例。我们观察到两个元素在UML中扮演着重要角色,即进行样本任务和衡量实例之间的相似性的方法。因此,我们获得了具有两个简单修改的​​强基线 - 一个足够的采样策略,每情节有效地构建多个任务以及半分解的相似性。然后,我们利用来自两个方向的任务特征以获得进一步的改进。首先,合成的混淆实例被合并以帮助提取更多的判别嵌入。其次,我们利用额外的特定任务嵌入转换作为元训练期间的辅助组件,以促进预先适应的嵌入式的概括能力。几乎没有学习基准的实验证明,我们的方法比以前的UML方法优于先前的UML方法,并且比其监督变体获得了可比甚至更好的性能。
translated by 谷歌翻译
少量学习,特别是几秒钟的图像分类,近年来受到了越来越多的关注,并目睹了重大进展。最近的一些研究暗示表明,许多通用技术或“诀窍”,如数据增强,预训练,知识蒸馏和自我监督,可能大大提高了几次学习方法的性能。此外,不同的作品可以采用不同的软件平台,不同的训练计划,不同的骨干架构以及甚至不同的输入图像大小,使得公平的比较困难,从业者与再现性斗争。为了解决这些情况,通过在Pytorch中的同一单个代码库中重新实施17个最新的框架,提出了几次射门学习(Libfewshot)的全面图书馆。此外,基于libfewshot,我们提供多个基准数据集的全面评估,其中包含多个骨干架构,以评估不同培训技巧的常见缺陷和效果。此外,鉴于近期对必要性或未培训机制的必要性怀疑,我们的评估结果表明,特别是当与预训练相结合时,仍然需要这种机制。我们希望我们的工作不仅可以降低初学者的障碍,可以在几次学习上工作,而且还消除了非动力技巧的影响,促进了几枪学习的内在研究。源代码可从https://github.com/rl-vig/libfewshot获取。
translated by 谷歌翻译
模型不合时宜的元学习(MAML)可以说是当今最流行的元学习算法之一。然而,它在几次分类上的性能远远远远远远远远远远远远远远落在许多致力于该问题的算法。在本文中,我们指出了如何训练MAML以进行几次分类的几个关键方面。首先,我们发现MAML在其内部循环更新中需要大量的梯度步骤,这与其常见的用法相矛盾。其次,我们发现MAML对元测试过程中的类标签分配敏感。具体而言,MAML Meta-Trains $ n$道分类器的初始化。这些$ n $方式,在元测试期间,然后具有“ $ n!$”的“ $ n!$”排列,并与$ n $新颖的课程配对。我们发现这些排列会导致巨大的准确性差异,从而使MAML不稳定。第三,我们研究了几种使MAML置换不变的方法,其中元训练单个向量以初始化分类头中的所有$ n $重量矢量的初始化。在Miniimagenet和Tieredimagenet等基准数据集上,我们命名Unicorn-MAML的方法在不牺牲MAML的简单性的情况下以与许多最近的几杆分类算法相同甚至优于许多近期的几个次数分类算法。
translated by 谷歌翻译
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. We empirically investigated various instantiations of such set-to-set functions and observed the Transformer is most effective -as it naturally satisfies key properties of our desired model. We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning. It archived consistent improvements over baseline models as well as previous methods, and established the new stateof-the-art results on two benchmarks.
translated by 谷歌翻译
少量分类需要调整从大型注释的基础数据集中学到的知识来识别新颖的看不见的类,每个类别由少数标记的示例表示。在这样的场景中,预先绘制大容量在大型数据集上的网络,然后在少数示例下向少量抵消导致严重的过度拟合。同时,在从大型标记数据集中学到的“冷冻”特征的顶部培训一个简单的线性分类器无法使模型调整到新型类的属性,有效地诱导底部。在本文中,我们向这两种流行的策略提出了一种替代方法。首先,我们的方法使用在新颖类上培训的线性分类器来伪标签整个大型数据集。这有效地“幻觉”在大型数据集中的新型类别,尽管基本数据库中未存在的新类别(新颖和基类是不相交的)。然后,除了在新型数据集上的标准交叉熵损失之外,它将在伪标记的基础示例上具有蒸馏损失的整个模型。这一步骤有效地训练了网络,识别对新型类别识别的上下文和外观提示,而是使用整个大规模基础数据集,从而克服了几次拍摄学习的固有数据稀缺问题。尽管这种方法的简单性,但我们表明我们的方法在四个成熟的少量分类基准上表现出最先进的。
translated by 谷歌翻译
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the mini-ImageNet and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.
translated by 谷歌翻译
很少有视觉识别是指从一些标记实例中识别新颖的视觉概念。通过将查询表示形式与类表征进行比较以预测查询实例的类别,许多少数射击的视觉识别方法采用了基于公制的元学习范式。但是,当前基于度量的方法通常平等地对待所有实例,因此通常会获得有偏见的类表示,考虑到并非所有实例在总结了类级表示的实例级表示时都同样重要。例如,某些实例可能包含无代表性的信息,例如过多的背景和无关概念的信息,这使结果偏差。为了解决上述问题,我们提出了一个新型的基于公制的元学习框架,称为实例自适应类别表示网络(ICRL-net),以进行几次视觉识别。具体而言,我们开发了一个自适应实例重新平衡网络,具有在生成班级表示,通过学习和分配自适应权重的不同实例中的自适应权重时,根据其在相应类的支持集中的相对意义来解决偏见的表示问题。此外,我们设计了改进的双线性实例表示,并结合了两个新型的结构损失,即,阶层内实例聚类损失和阶层间表示区分损失,以进一步调节实例重估过程并完善类表示。我们对四个通常采用的几个基准测试:Miniimagenet,Tieredimagenet,Cifar-FS和FC100数据集进行了广泛的实验。与最先进的方法相比,实验结果证明了我们的ICRL-NET的优势。
translated by 谷歌翻译
Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve generalization performance. However, the contribution of pre-training is often overlooked and understudied, with limited theoretical understanding of its impact on meta-learning performance. Further, pre-training requires a consistent set of global labels shared across training tasks, which may be unavailable in practice. In this work, we address the above issues by first showing the connection between pre-training and meta-learning. We discuss why pre-training yields more robust meta-representation and connect the theoretical analysis to existing works and empirical results. Secondly, we introduce Meta Label Learning (MeLa), a novel meta-learning algorithm that learns task relations by inferring global labels across tasks. This allows us to exploit pre-training for FSL even when global labels are unavailable or ill-defined. Lastly, we introduce an augmented pre-training procedure that further improves the learned meta-representation. Empirically, MeLa outperforms existing methods across a diverse range of benchmarks, in particular under a more challenging setting where the number of training tasks is limited and labels are task-specific. We also provide extensive ablation study to highlight its key properties.
translated by 谷歌翻译
元学习可以从先前的学习体验中提取归纳偏见,并协助培训新任务。通常通过优化特定于任务求解器的评估损失来实现META模型来实现。大多数现有算法样本非重叠$ \ mathit {support} $ sets和$ \ mathit {查询} $ sets以分别为培训和评估求解器($ \ mathcal {s} $ / $ \ mathcal {q} $协议)。不同于$ \ mathcal {s} $ / $ \ mathcal {q} $协议,我们还可以通过将其与目标型号$ \ mathcal {t} $进行比较来评估任务特定的求解器,这是它的最佳模型任务或在此任务中足够好的模型($ \ mathcal {s} $ / $ \ mathcal {t} $协议)。虽然研究短缺,但$ \ mathcal {s} $ / $ \ mathcal {t} $协议具有独特的优势,如提供更具信息性的监督,但它是计算昂贵的。本文研究了这种特殊的评估方法,迈出了将它付诸实践。我们发现,通过掌握目标模型的任务比例小,可以提高经典的元学习算法,而不会消耗许多资源。我们在典型的Meta-Learning,$ \ Mathit {i.} $,几秒钟学习中验证$ \ mathcal {s} $ / $ \ mathcal {t} $协议的有效性。详细地,在通过微调预先调整那些硬任务的预先训练网络之后构建目标模型之后,我们通过知识蒸馏匹配任务特定的求解器和目标模型。
translated by 谷歌翻译
现有的少量学习(FSL)方法依赖于具有大型标记数据集的培训,从而阻止它们利用丰富的未标记数据。从信息理论的角度来看,我们提出了一种有效的无监督的FSL方法,并以自学意义进行学习表示。遵循信息原理,我们的方法通过捕获数据的内在结构来学习全面的表示。具体而言,我们以低偏置的MI估计量来最大化实例及其表示的相互信息(MI),以执行自我监督的预训练。我们的自我监督模型对所见类别的可区分特征的监督预训练没有针对可见的阶级的偏见,从而对看不见的类别进行了更好的概括。我们解释说,受监督的预训练和自我监督的预训练实际上正在最大化不同的MI目标。进一步进行了广泛的实验,以通过各种训练环境分析其FSL性能。令人惊讶的是,结果表明,在适当条件下,自我监管的预训练可以优于监督预训练。与最先进的FSL方法相比,我们的方法在没有基本类别的任何标签的情况下,在广泛使用的FSL基准上实现了可比的性能。
translated by 谷歌翻译
在这项工作中,我们建议使用分布式样本,即来自目标类别外部的未标记样本,以改善几乎没有记录的学习。具体而言,我们利用易于可用的分布样品来驱动分类器,以避免通过最大化原型到分布样品的距离,同时最大程度地减少分布样品的距离(即支持,查询数据),以避免使用分类器。。我们的方法易于实施,不可知论的是提取器,轻量级,而没有任何额外的预训练费用,并且适用于归纳和跨传输设置。对各种标准基准测试的广泛实验表明,所提出的方法始终提高具有不同架构的预审计网络的性能。
translated by 谷歌翻译
Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks. Our objective is to learn feature embeddings that generalize well under a linear classification rule for novel categories. To efficiently solve the objective, we exploit two properties of linear classifiers: implicit differentiation of the optimality conditions of the convex problem and the dual formulation of the optimization problem. This allows us to use highdimensional embeddings with improved generalization at a modest increase in computational overhead. Our approach, named MetaOptNet, achieves state-of-the-art performance on miniImageNet, tieredImageNet, CIFAR-FS, and FC100 few-shot learning benchmarks. Our code is available online 1 .
translated by 谷歌翻译
少量分类旨在通过一些培训样本来调整小型课程的分类器。然而,训练数据的不足可能导致某个类中的特征分布偏差估计。为了缓解这个问题,我们通过探索新颖和基类之间的类别相关性,作为先前知识来展示一个简单而有效的功能整流方法。我们通过将特征映射到潜在的向量中明确地捕获这种相关性,其中匹配基类的数量的维度,将其视为在基类上的特征的对数概率。基于该潜伏向量,整流特征由解码器直接构建,我们预计在去除其他随机因素的同时保持与类别相关的信息,因此更接近其类心。此外,通过改变SoftMax中的温度值,我们可以重新平衡特征整流和重建以获得更好的性能。我们的方法是通用的,灵活的,不可知的任何特征提取器和分类器,容易嵌入到现有的FSL方法中。实验验证了我们的方法能够整流偏置功能,尤其是当特征远离班级质心时。拟议的方法一直在三种广泛使用的基准上获得相当大的性能收益,用不同的骨干和分类器评估。该代码将公开。
translated by 谷歌翻译
The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great practical values in the real-world applications. Despite extensive previous efforts are made on few-shot learning tasks, we emphasize that most existing methods did not take into account the distributional shift caused by sample selection bias in the FSL scenario. Such a selection bias can induce spurious correlation between the semantic causal features, that are causally and semantically related to the class label, and the other non-causal features. Critically, the former ones should be invariant across changes in distributions, highly related to the classes of interest, and thus well generalizable to novel classes, while the latter ones are not stable to changes in the distribution. To resolve this problem, we propose a novel data augmentation strategy dubbed as PatchMix that can break this spurious dependency by replacing the patch-level information and supervision of the query images with random gallery images from different classes from the query ones. We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features. To further make these features to be discriminative enough for classification, we propose Correlation-guided Reconstruction (CGR) and Hardness-Aware module for instance discrimination and easier discrimination between similar classes. Moreover, such a framework can be adapted to the unsupervised FSL scenario.
translated by 谷歌翻译
大多数现有的工作在几次学习中,依赖于Meta-Learning网络在大型基础数据集上,该网络通常是与目标数据集相同的域。我们解决了跨域几秒钟的问题,其中基础和目标域之间存在大移位。与未标记的目标数据的跨域几秒识别问题在很大程度上在文献中毫无根据。启动是使用自我训练解决此问题的第一个方法。但是,它使用固定的老师在标记的基础数据集上返回,以为未标记的目标样本创建软标签。由于基本数据集和未标记的数据集来自不同的域,因此将基本数据集的类域中的目标图像投影,具有固定的预制模型可能是子最优的。我们提出了一种简单的动态蒸馏基方法,以方便来自新颖/基础数据集的未标记图像。我们通过从教师网络中的未标记图像的未标记版本的预测计算并将其与来自学生网络相同的相同图像的强大版本匹配来施加一致性正常化。教师网络的参数被更新为学生网络参数的指数移动平均值。我们表明所提出的网络了解可以轻松适应目标域的表示,即使它尚未在预先预测阶段的目标专用类别训练。我们的车型优于当前最先进的方法,在BSCD-FSL基准中的5次分类,3.6%的3.6%,并在传统的域名几枪学习任务中显示出竞争性能。
translated by 谷歌翻译
Despite the success that metric learning based approaches have achieved in few-shot learning, recent works reveal the ineffectiveness of their episodic training mode. In this paper, we point out two potential reasons for this problem: 1) the random episodic labels can only provide limited supervision information, while the relatedness information between the query and support samples is not fully exploited; 2) the meta-learner is usually constrained by the limited contextual information of the local episode. To overcome these problems, we propose a new Global Relatedness Decoupled-Distillation (GRDD) method using the global category knowledge and the Relatedness Decoupled-Distillation (RDD) strategy. Our GRDD learns new visual concepts quickly by imitating the habit of humans, i.e. learning from the deep knowledge distilled from the teacher. More specifically, we first train a global learner on the entire base subset using category labels as supervision to leverage the global context information of the categories. Then, the well-trained global learner is used to simulate the query-support relatedness in global dependencies. Finally, the distilled global query-support relatedness is explicitly used to train the meta-learner using the RDD strategy, with the goal of making the meta-learner more discriminative. The RDD strategy aims to decouple the dense query-support relatedness into the groups of sparse decoupled relatedness. Moreover, only the relatedness of a single support sample with other query samples is considered in each group. By distilling the sparse decoupled relatedness group by group, sharper relatedness can be effectively distilled to the meta-learner, thereby facilitating the learning of a discriminative meta-learner. We conduct extensive experiments on the miniImagenet and CIFAR-FS datasets, which show the state-of-the-art performance of our GRDD method.
translated by 谷歌翻译
从一个非常少数标记的样品中学习新颖的课程引起了机器学习区域的越来越高。最近关于基于元学习或转移学习的基于范例的研究表明,良好特征空间的获取信息可以是在几次拍摄任务上实现有利性能的有效解决方案。在本文中,我们提出了一种简单但有效的范式,该范式解耦了学习特征表示和分类器的任务,并且只能通过典型的传送学习培训策略从基类嵌入体系结构的特征。为了在每个类别内保持跨基地和新类别和辨别能力的泛化能力,我们提出了一种双路径特征学习方案,其有效地结合了与对比特征结构的结构相似性。以这种方式,内部级别对齐和级别的均匀性可以很好地平衡,并且导致性能提高。三个流行基准测试的实验表明,当与简单的基于原型的分类器结合起来时,我们的方法仍然可以在电感或转换推理设置中的标准和广义的几次射击问题达到有希望的结果。
translated by 谷歌翻译
很少拍摄的学习解决了学习如何解决不仅仅是有限的监督而且有限的数据的挑战。有吸引力的解决方案是合成数据生成。然而,大多数此类方法过于复杂,专注于输入空间中的高质量现实数据。目前尚不清楚是否将它们适应少次拍摄的制度并使用它们在分类的下游任务中是正确的方法。以前关于综合数据生成的工作,用于几次分类专注于利用复杂模型,例如,具有多个常规方或网络的Wasserstein GaN,可从新颖的课程中传输潜在的分集。我们遵循不同的方法,并调查如何有效地使用简单和简单的合成数据生成方法。我们提出了两个贡献,即我们表明:(1)使用简单的损失函数足以训练几次拍摄设置中的一个特征生成器; (2)学习生成张量特征而不是矢量特征是优越的。在MiniimAgenet,Cub和CiFar-FS数据集上的广泛实验表明,我们的方法设置了新的最新状态,优于更复杂的少量数据增强方法。源代码可以在https://github.com/michalislazarou/tfh_fewshot找到。
translated by 谷歌翻译