课堂学习学习需要可塑性和稳定性，以便在保留过去的知识的同时从新数据中学习。由于灾难性的遗忘，当没有内存缓冲区可用时，在这两个属性之间找到妥协尤其具有挑战性。主流方法需要存储两个深层模型，因为它们使用微调与以前的增量状态的知识蒸馏一起整合了新类。我们提出了一种具有相似数量参数但分布不同的方法，以便在可塑性和稳定性之间找到更好的平衡。遵循已经通过基于转移的增量方法部署的方法，我们在初始状态后冻结了功能提取器。最古老的增量状态的类对这种冷冻提取器进行训练，以确保稳定性。使用部分微调模型预测最近的类别以引入可塑性。我们提出的可塑性层可以纳入任何用于无内存增量学习的基于转移的方法，并将其应用于两种此类方法。评估是通过三个大型数据集进行的。结果表明，与现有方法相比，所有测试的配置中均获得了性能提高。

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added incrementally. This is due to current neural network architectures requiring the entire dataset, consisting of all the samples from the old as well as the new classes, to update the model-a requirement that becomes easily unsustainable as the number of classes grows. We address this issue with our approach to learn deep neural networks incrementally, using new data and only a small exemplar set corresponding to samples from the old classes. This is based on a loss composed of a distillation measure to retain the knowledge acquired from the old classes, and a cross-entropy loss to learn the new classes. Our incremental training is achieved while keeping the entire framework end-to-end, i.e., learning the data representation and the classifier jointly, unlike recent methods with no such guarantees. We evaluate our method extensively on the CIFAR-100 and Im-ageNet (ILSVRC 2012) image classification datasets, and show state-of-the-art performance.

Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning. In this work, we propose PODNet, a model inspired by representation learning. By carefully balancing the compromise between remembering the old classes and learning new ones, PODNet fights catastrophic forgetting, even over very long runs of small incremental tasks -a setting so far unexplored by current works. PODNet innovates on existing art with an efficient spatialbased distillation-loss applied throughout the model and a representation comprising multiple proxy vectors for each class. We validate those innovations thoroughly, comparing PODNet with three state-of-the-art models on three datasets: CIFAR100, ImageNet100, and ImageNet1000. Our results showcase a significant advantage of PODNet over existing art, with accuracy gains of 12.10, 6.51, and 2.85 percentage points, respectively. 5

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。

A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a classincremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively.iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail.

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.

这项工作调查了持续学习（CL）与转移学习（TL）之间的纠缠。特别是，我们阐明了网络预训练的广泛应用，强调它本身受到灾难性遗忘的影响。不幸的是，这个问题导致在以后任务期间知识转移的解释不足。在此基础上，我们提出了转移而不忘记（TWF），这是在固定的经过预定的兄弟姐妹网络上建立的混合方法，该方法不断传播源域中固有的知识，通过层次损失项。我们的实验表明，TWF在各种设置上稳步优于其他CL方法，在各种数据集和不同的缓冲尺寸上，平均每种类型的精度增长了4.81％。

在学习新知识时，班级学习学习（CIL）与灾难性遗忘和无数据CIL（DFCIL）的斗争更具挑战性，而无需访问以前学过的课程的培训数据。尽管最近的DFCIL作品介绍了诸如模型反转以合成以前类的数据，但由于合成数据和真实数据之间的严重域间隙，它们无法克服遗忘。为了解决这个问题，本文提出了有关DFCIL的关系引导的代表学习（RRL），称为R-DFCIL。在RRL中，我们引入了关系知识蒸馏，以灵活地将新数据的结构关系从旧模型转移到当前模型。我们的RRL增强DFCIL可以指导当前的模型来学习与以前类的表示更好地兼容的新课程的表示，从而大大减少了在改善可塑性的同时遗忘。为了避免表示和分类器学习之间的相互干扰，我们在RRL期间采用本地分类损失而不是全球分类损失。在RRL之后，分类头将通过全球类平衡的分类损失进行完善，以解决数据不平衡问题，并学习新课程和以前类之间的决策界限。关于CIFAR100，Tiny-Imagenet200和Imagenet100的广泛实验表明，我们的R-DFCIL显着超过了以前的方法，并实现了DFCIL的新最新性能。代码可从https://github.com/jianzhangcs/r-dfcil获得。

我们考虑了类增量学习（CIL）问题，其中学习代理人通过逐步到达的培训数据批次不断学习新课程，并旨在在迄今为止所学的所有课程中很好地预测。问题的主要挑战是灾难性的遗忘，对于基于典范的示例性记忆方法，通常众所周知，遗忘通常是由于分类评分偏差引起的，该分类得分偏差是由于新类和新类之间的数据失衡而注射的旧课（在示例记忆中）。尽管已经提出了几种方法来通过一些其他后处理（例如，得分重新缩放或平衡的微调）来纠正这种分数偏见，但没有对这种偏见的根本原因进行系统分析。为此，我们分析了通过组合所有旧类和新类的输出得分来计算SoftMax概率的主要原因。然后，我们提出了一种新方法，称为分离的软磁性学习（SS-IL），该方法由分离的SoftMax（SS）输出层组成，结合了任务知识蒸馏（TKD）来解决此类偏见。在几个大规模CIL基准数据集的广泛实验结果中，我们通过在没有任何其他后处理的情况下获得更加平衡的预测分数来表明我们的SS-IL实现了强大的最新准确性。

我们研究了类新型小说类发现的新任务（class-incd），该任务是指在未标记的数据集中发现新型类别的问题，该问题通过利用已在包含脱节的标签数据集上训练的预训练的模型，该模型已受过培训但是相关类别。除了发现新颖的课程外，我们还旨在维护模型识别先前看到的基本类别的能力。受到基于彩排的增量学习方法的启发，在本文中，我们提出了一种新颖的方法，以防止通过共同利用基类功能原型和特征级知识蒸馏来忘记对基础类的过去信息。我们还提出了一种自我训练的聚类策略，该策略同时将新颖的类别簇簇，并为基础和新颖类培训共同分类器。这使得我们的方法能够在课堂内设置中运行。我们的实验以三个共同的基准进行，表明我们的方法显着优于最先进的方法。代码可从https://github.com/oatmealliu/class-incd获得

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the training on subsequent tasks. However, this is not always possible, e.g., due to data protection regulations. In such restricted scenarios, one can employ generative models to replay either artificial images or hidden features to a classifier. In this work, we propose Genifer (GENeratIve FEature-driven image Replay), where a generative model is trained to replay images that must induce the same hidden features as real samples when they are passed through the classifier. Our technique therefore incorporates the benefits of both image and feature replay, i.e.: (1) unlike conventional image replay, our generative model explicitly learns the distribution of features that are relevant for classification; (2) in contrast to feature replay, our entire classifier remains trainable; and (3) we can leverage image-space augmentations, which increase distillation performance while also mitigating overfitting during the training of the generative model. We show that Genifer substantially outperforms the previous state of the art for various settings on the CIFAR-100 and CUB-200 datasets.

人类的持续学习（CL）能力与稳定性与可塑性困境密切相关，描述了人类如何实现持续的学习能力和保存的学习信息。自发育以来，CL的概念始终存在于人工智能（AI）中。本文提出了对CL的全面审查。与之前的评论不同，主要关注CL中的灾难性遗忘现象，本文根据稳定性与可塑性机制的宏观视角来调查CL。类似于生物对应物，“智能”AI代理商应该是I）记住以前学到的信息（信息回流）; ii）不断推断新信息（信息浏览:); iii）转移有用的信息（信息转移），以实现高级CL。根据分类学，评估度量，算法，应用以及一些打开问题。我们的主要贡献涉及I）从人工综合情报层面重新检查CL; ii）在CL主题提供详细和广泛的概述; iii）提出一些关于CL潜在发展的新颖思路。

持续学习（CL）旨在制定模仿人类能力顺序学习新任务的能力，同时能够保留从过去经验获得的知识。在本文中，我们介绍了内存约束在线连续学习（MC-OCL）的新问题，这对存储器开销对可能算法可以用于避免灾难性遗忘的记忆开销。最多，如果不是全部，之前的CL方法违反了这些约束，我们向MC-OCL提出了一种算法解决方案：批量蒸馏（BLD），基于正则化的CL方法，有效地平衡了稳定性和可塑性，以便学习数据流，同时保留通过蒸馏解决旧任务的能力。我们在三个公开的基准测试中进行了广泛的实验评估，经验证明我们的方法成功地解决了MC-OCL问题，并实现了需要更高内存开销的先前蒸馏方法的可比准确性。

恶意软件（恶意软件）分类为持续学习（CL）制度提供了独特的挑战，这是由于每天收到的新样本的数量以及恶意软件的发展以利用新漏洞。在典型的一天中，防病毒供应商将获得数十万个独特的软件，包括恶意和良性，并且在恶意软件分类器的一生中，有超过十亿个样品很容易积累。鉴于问题的规模，使用持续学习技术的顺序培训可以在减少培训和存储开销方面提供可观的好处。但是，迄今为止，还没有对CL应用于恶意软件分类任务的探索。在本文中，我们研究了11种应用于三个恶意软件任务的CL技术，涵盖了常见的增量学习方案，包括任务，类和域增量学习（IL）。具体而言，使用两个现实的大规模恶意软件数据集，我们评估了CL方法在二进制恶意软件分类（domain-il）和多类恶意软件家庭分类（Task-IL和类IL）任务上的性能。令我们惊讶的是，在几乎所有情况下，持续的学习方法显着不足以使训练数据的幼稚关节重播 - 在某些情况下，将精度降低了70个百分点以上。与关节重播相比，有选择性重播20％的存储数据的一种简单方法可以实现更好的性能，占训练时间的50％。最后，我们讨论了CL技术表现出乎意料差的潜在原因，希望它激发进一步研究在恶意软件分类域中更有效的技术。

在从少数类（基类）开始的情况下，已经广泛研究了课堂学习学习（CIL）。取而代之的是，我们探索了一个研究不足的CIL现实环境，该设置是从在大量基类中进行预训练的强大模型开始。我们假设强大的基本模型可以为新颖的类别提供良好的表示，并且可以通过小型适应来进行渐进的学习。我们提出了一个2阶段的训练方案，i）功能增强 - 将部分的克隆部分克隆并在新型数据上进行微调，ii）融合 - 将基础和新型分类器组合到统一的分类器中。实验表明，所提出的方法在大型成像网数据集上的最先进的CIL方法明显优于最先进的CIL方法（例如，总体准确度 +最佳 +最佳精度为10％）。我们还建议和分析研究研究的实际CIL方案，例如与分布转移的基础新颖性重叠。我们提出的方法是鲁棒的，并概括了所有分析的CIL设置。代码可从https://github.com/amazon-research/sp-cil获得。

当在新的类或新任务上逐步训练时，深度神经网络易于灾难性遗忘，因为对新数据的适应导致旧课程和任务的性能急剧下降。通过使用小记忆进行排练和知识蒸馏，已证明最近的方法可有效缓解灾难性的遗忘。然而，由于内存的尺寸有限，旧的和新类可用的数据量之间的大不平衡仍然存在，这导致模型的整体精度恶化。为了解决这个问题，我们建议使用平衡的软制跨熵损失，并表明它可以与进出的方法相结合，以便在某些情况下降低培训过程的计算成本，以提高其性能。对竞争的想象，Subimagenet和CiFar100数据集的实验显示了最艺术态度的结果。

Conventionally, deep neural networks are trained offline, relying on a large dataset prepared in advance. This paradigm is often challenged in real-world applications, e.g. online services that involve continuous streams of incoming data. Recently, incremental learning receives increasing attention, and is considered as a promising solution to the practical challenges mentioned above. However, it has been observed that incremental learning is subject to a fundamental difficulty -catastrophic forgetting, namely adapting a model to new data often results in severe performance degradation on previous tasks or classes. Our study reveals that the imbalance between previous and new data is a crucial cause to this problem. In this work, we develop a new framework for incrementally learning a unified classifier, i.e. a classifier that treats both old and new classes uniformly. Specifically, we incorporate three components, cosine normalization, less-forget constraint, and inter-class separation, to mitigate the adverse effects of the imbalance. Experiments show that the proposed method can effectively rebalance the training process, thus obtaining superior performance compared to the existing methods. On CIFAR-100 and ImageNet, our method can reduce the classification errors by more than 6% and 13% respectively, under the incremental setting of 10 phases.

本文在课堂增量学习中使用视觉变压器（VIT）研究。令人惊讶的是，天真地应用Vit替代卷积神经网络（CNNS）导致性能下降。我们的分析揭示了三个天然使用VIT的问题：（a）vit在课程中较小时具有非常缓慢的会聚，（b）在比CNN的模型中观察到新类的更多偏差，并且（c）适当的学习率Vit太低，无法学习良好的分类器。基于此分析，我们展示了这些问题可以简单地通过使用现有技术来解决：使用卷积杆，平衡FineTuning来纠正偏置，以及分类器的更高学习率。我们的简单解决方案名为Vitil（Vit用于增量学习），为所有三类增量学习设置实现了全新的最先进的保证金，为研究界提供了强大的基线。例如，在ImageNet-1000上，我们的体内体达到69.20％的前1个精度为500个初始类别的15个初始类别，5个增量步骤（每次100个新类），表现优于leulir + dde ​​1.69％。对于10个增量步骤（100个新课程）的更具挑战性的协议，我们的方法优于PODNet 7.27％（65.13％与57.86％）。

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.