Representation learningLow-shot learning Feature extractor Base classes (many training examples)Classifier (base and novel categories) Novel classes (few training examples)Figure 1: Our low-shot learning benchmark in two phases: representation learning and low-shot learning. Modern recognition models use large labeled datasets like ImageNet to build good visual representations and train strong classifiers (representation learning).However, these datasets only contain a fixed set of classes. In many realistic scenarios, once deployed, the model might encounter novel classes that it also needs to recognize, but with very few training examples available (low-shot learning). We present two ways of significantly improving performance in this scenario: (1) a novel loss function for representation learning that leads to better visual representations that generalize well, and (2) a method for hallucinating additional examples for the data-starved novel classes.

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research problem with many practical advantages on real world vision applications. In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories). To achieve that goal we propose (a) to extend an object recognition system with an attention based few-shot classification weight generator, and (b) to redesign the classifier of a ConvNet model as the cosine similarity function between feature representations and classification weight vectors. The latter, apart from unifying the recognition of both novel and base categories, it also leads to feature representations that generalize better on "unseen" categories. We extensively evaluate our approach on Mini-ImageNet where we manage to improve the prior state-of-the-art on few-shot recognition (i.e., we achieve 56.20% and 73.00% on the 1-shot and 5-shot settings respectively) while at the same time we do not sacrifice any accuracy on the base categories, which is a characteristic that most prior approaches lack. Finally, we apply our approach on the recently introduced few-shot benchmark of Bharath and Girshick [4] where we also achieve stateof-the-art results. The code and models of our paper will be published on: https://github.com/gidariss/ FewShotWithoutForgetting.

Human vision is able to immediately recognize novel visual categories after seeing just one or a few training examples. We describe how to add a similar capability to ConvNet classifiers by directly setting the final layer weights from novel training examples during low-shot learning. We call this process weight imprinting as it directly sets weights for a new category based on an appropriately scaled copy of the embedding layer activations for that training example. The imprinting process provides a valuable complement to training with stochastic gradient descent, as it provides immediate good classification performance and an initialization for any further fine-tuning in the future. We show how this imprinting process is related to proxy-based embeddings. However, it differs in that only a single imprinted weight vector is learned for each novel category, rather than relying on a nearest-neighbor distance to training instances as typically used with embedding methods. Our experiments show that using averaging of imprinted weights provides better generalization than using nearest-neighbor instance embeddings.

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。

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.

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 .

Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100. Our code is publicly available at https://github.com/ElementAI/TADAM.

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。

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.

很少有射击分类旨在仅使用几个标签示例就可以很好地学习新对象类别。从其他模型转移功能表示是一种流行的方法，用于解决几乎没有射击的分类问题。在这项工作中，我们对各种功能表示形式进行了系统的研究，以进行几次射击分类，包括从MAML中学到的表示，监督分类和几个常见的自我监督任务。我们发现，从更复杂的任务中学习倾向于为几个射击分类提供更好的表示，因此我们建议使用从多个任务中学到的表示形式进行几次分类。加上功能选择和投票以处理小样本量的新技巧，我们的直接转移学习方法提供的性能可与几个基准数据集上的最先进相提并论。

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on five benchmarks demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel objects from only a few annotated examples. Our proposed model leverages fully labeled base classes and quickly adapts to novel classes, using a meta feature learner and a reweighting module within a one-stage detection architecture. The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples. The reweighting module transforms a few support examples from the novel classes to a global vector that indicates the importance or relevance of meta features for detecting the corresponding objects. These two modules, together with a detection prediction module, are trained end-to-end based on an episodic few-shot learning scheme and a carefully designed loss function. Through extensive experiments we demonstrate that our model outperforms well-established baselines by a large margin for few-shot object detection, on multiple datasets and settings. We also present analysis on various aspects of our proposed model, aiming to provide some inspiration for future few-shot detection works.

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。

在新课程训练时，几乎没有射击学习（FSL）方法通常假设具有准确标记的样品的清洁支持集。这个假设通常可能是不现实的：支持集，无论多么小，仍然可能包括标签错误的样本。因此，对标签噪声的鲁棒性对于FSL方法是实用的，但是这个问题令人惊讶地在很大程度上没有探索。为了解决FSL设置中标签错误的样品，我们做出了一些技术贡献。 （1）我们提供了简单而有效的特征聚合方法，改善了流行的FSL技术Protonet使用的原型。 （2）我们描述了一种嘈杂的噪声学习的新型变压器模型（TRANFS）。 TRANFS利用变压器的注意机制称重标记为错误的样品。 （3）最后，我们对迷你胶原和tieredimagenet的嘈杂版本进行了广泛的测试。我们的结果表明，TRANFS与清洁支持集的领先FSL方法相对应，但到目前为止，在存在标签噪声的情况下，它们的表现优于它们。

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.

We address the problem of few-shot classification where the goal is to learn a classifier from a limited set of samples. While data-driven learning is shown to be effective in various applications, learning from less data still remains challenging. To address this challenge, existing approaches consider various data augmentation techniques for increasing the number of training samples. Pseudo-labeling is commonly used in a few-shot setup, where approximate labels are estimated for a large set of unlabeled images. We propose DiffAlign which focuses on generating images from class labels. Specifically, we leverage the recent success of the generative models (e.g., DALL-E and diffusion models) that can generate realistic images from texts. However, naive learning on synthetic images is not adequate due to the domain gap between real and synthetic images. Thus, we employ a maximum mean discrepancy (MMD) loss to align the synthetic images to the real images minimizing the domain gap. We evaluate our method on the standard few-shot classification benchmarks: CIFAR-FS, FC100, miniImageNet, tieredImageNet and a cross-domain few-shot classification benchmark: miniImageNet to CUB. The proposed approach significantly outperforms the stateof-the-art in both 5-shot and 1-shot setups on these benchmarks. Our approach is also shown to be effective in the zero-shot classification setup

现代ML方法在培训数据是IID，大规模和良好标记的时候Excel。在不太理想的条件下学习仍然是一个开放的挑战。在不利条件下，几次射击，持续的，转移和代表学习的子场在学习中取得了很大的进步;通过方法和见解，每个都提供了独特的优势。这些方法解决了不同的挑战，例如依次到达的数据或稀缺的训练示例，然而，在部署之前，ML系统将面临困难的条件。因此，需要可以处理实际设置中许多学习挑战的一般ML系统。为了促进一般ML方法目标的研究，我们介绍了一个新的统一评估框架 - 流体（灵活的顺序数据）。流体集成了几次拍摄，持续的，转移和表示学习的目标，同时能够比较和整合这些子场的技术。在流体中，学习者面临数据流，并且必须在选择如何更新自身时进行顺序预测，快速调整到新颖的类别，并处理更改的数据分布;虽然会计计算总额。我们对广泛的方法进行实验，这些方法阐述了新的洞察当前解决方案的优缺点并表明解决了新的研究问题。作为更一般方法的起点，我们展示了两种新的基线，其在流体上优于其他评估的方法。项目页面：https：//raivn.cs.washington.edu/projects/fluid/。

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。

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。