近年来,在各种特定于任务的情况下,盲目图像质量评估(BIQA)取得了巨大的成功,这些方案呈现出不变的失真类型和评估标准。但是,由于刚性结构和学习框架,它们不能应用于交叉任务BIQA方案,在这种情况下,失真类型和评估标准在实际应用中不断变化。本文提出了一个可扩展的增量学习框架(SILF),该框架可以在多个评估任务中依次执行BIQA,具有有限的记忆能力。更具体地说,我们开发了动态参数隔离策略,以依次更新特定于任务的参数子集,这些参数子集彼此之间并非重叠。每个参数子集都会暂时解决,以记住对其相应任务的一个评估偏好,并且可以在以下BIQA中自适应地重复使用先前的参数子集,以根据任务相关性实现更好的性能。为了抑制顺序任务学习中记忆容量的不受限制扩展,我们通过从先前解决的参数子集中逐渐和选择性地修剪不重要的神经元来开发可扩展的内存单元,这使我们能够忘记以前的经验的一部分,并释放有限的内存能力,以适应适应新的新任务。对11个IQA数据集进行的广泛实验表明,我们提出的方法在交叉任务BIQA中的其他最新方法显着优于其他最新方法。
translated by 谷歌翻译
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.
translated by 谷歌翻译
当在具有不同分布的数据集上不断学习时,神经网络往往会忘记以前学习的知识,这一现象被称为灾难性遗忘。数据集之间的分配更改会导致更多的遗忘。最近,基于参数 - 隔离的方法在克服遗忘时具有巨大的潜力。但是,当他们在培训过程中修复每个数据集的神经路径时,他们的概括不佳,并且在推断过程中需要数据集标签。此外,他们不支持向后的知识转移,因为它们优先于过去的数据。在本文中,我们提出了一种名为ADAPTCL的新的自适应学习方法,该方法完全重复使用并在学习的参数上生长,以克服灾难性的遗忘,并允许在不需要数据集标签的情况下进行积极的向后传输。我们提出的技术通过允许最佳的冷冻参数重复使用在相同的神经路径上生长。此外,它使用参数级数据驱动的修剪来为数据分配同等优先级。我们对MNIST变体,域和食物新鲜度检测数据集进行了广泛的实验,而无需数据集标签。结果表明,我们所提出的方法优于替代基线,可以最大程度地减少遗忘和实现积极的向后知识转移。
translated by 谷歌翻译
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。
translated by 谷歌翻译
可扩展的网络已经证明了它们在处理灾难性遗忘问题方面的优势。考虑到不同的任务可能需要不同的结构,最近的方法设计了通过复杂技能适应不同任务的动态结构。他们的例程是首先搜索可扩展的结构,然后训练新任务,但是,这将任务分为多个培训阶段,从而导致次优或过度计算成本。在本文中,我们提出了一个名为E2-AEN的端到端可训练的可自适应扩展网络,该网络动态生成了新任务的轻量级结构,而没有任何精确的先前任务下降。具体而言,该网络包含一个功能强大的功能适配器的序列,用于扩大以前学习的表示新任务的表示形式,并避免任务干扰。这些适配器是通过基于自适应门的修剪策略来控制的,该策略决定是否可以修剪扩展的结构,从而根据新任务的复杂性动态地改变网络结构。此外,我们引入了一种新颖的稀疏激活正则化,以鼓励模型学习具有有限参数的区分特征。 E2-aen可以降低成本,并且可以以端到端的方式建立在任何饲喂前架构上。关于分类(即CIFAR和VDD)和检测(即可可,VOC和ICCV2021 SSLAD挑战)的广泛实验证明了提出的方法的有效性,从而实现了新的出色结果。
translated by 谷歌翻译
由于存在于视觉信号采集,压缩,传输和显示的各个阶段的质量降级,图像质量评估(IQA)在基于图像的应用中起着重要作用。根据参考图像是否完整且可用,图像质量评估可分为三类:全引用(FR),减少参考(RR)和非引用(NR)。本文将审查最先进的图像质量评估算法。
translated by 谷歌翻译
This paper presents a method for adding multiple tasks to a single deep neural network while avoiding catastrophic forgetting. Inspired by network pruning techniques, we exploit redundancies in large deep networks to free up parameters that can then be employed to learn new tasks. By performing iterative pruning and network re-training, we are able to sequentially "pack" multiple tasks into a single network while ensuring minimal drop in performance and minimal storage overhead. Unlike prior work that uses proxy losses to maintain accuracy on older tasks, we always optimize for the task at hand. We perform extensive experiments on a variety of network architectures and largescale datasets, and observe much better robustness against catastrophic forgetting than prior work. In particular, we are able to add three fine-grained classification tasks to a single ImageNet-trained VGG-16 network and achieve accuracies close to those of separately trained networks for each task. Code available at https://github.com/ arunmallya/packnet
translated by 谷歌翻译
在过去的几十年中,盲目的图像质量评估(BIQA)旨在准确地预测图像质量而无需任何原始参考信息,但一直在广泛关注。特别是,在深层神经网络的帮助下,取得了巨大进展。但是,对于夜间图像(NTI)的BIQA的研究仍然较少,通常患有复杂的真实扭曲,例如可见性降低,低对比度,添加噪声和颜色失真。这些多样化的真实降解特别挑战了有效的深神网络的设计,用于盲目NTI质量评估(NTIQE)。在本文中,我们提出了一个新颖的深层分解和双线性池网络(DDB-NET),以更好地解决此问题。 DDB-NET包含三个模块,即图像分解模块,一个特征编码模块和双线性池模块。图像分解模块的灵感来自Itinex理论,并涉及将输入NTI解耦到负责照明信息的照明层组件和负责内容信息的反射层组件。然后,编码模块的功能涉及分别植根于两个解耦组件的降解的特征表示。最后,通过将照明相关和与内容相关的降解作为两因素变化进行建模,将两个特征集组合在一起,将双线汇总在一起以形成统一的表示,以进行质量预测。在几个基准数据集上进行了广泛的实验,已对所提出的DDB-NET的优势得到了很好的验证。源代码将很快提供。
translated by 谷歌翻译
持续学习旨在快速,不断地从一系列任务中学习当前的任务。与其他类型的方法相比,基于经验重播的方法表现出了极大的优势来克服灾难性的遗忘。该方法的一个常见局限性是上一个任务和当前任务之间的数据不平衡,这将进一步加剧遗忘。此外,如何在这种情况下有效解决稳定性困境也是一个紧迫的问题。在本文中,我们通过提出一个通过多尺度知识蒸馏和数据扩展(MMKDDA)提出一个名为Meta学习更新的新框架来克服这些挑战。具体而言,我们应用多尺度知识蒸馏来掌握不同特征级别的远程和短期空间关系的演变,以减轻数据不平衡问题。此外,我们的方法在在线持续训练程序中混合了来自情节记忆和当前任务的样品,从而减轻了由于概率分布的变化而减轻了侧面影响。此外,我们通过元学习更新来优化我们的模型,该更新诉诸于前面所看到的任务数量,这有助于保持稳定性和可塑性之间的更好平衡。最后,我们对四个基准数据集的实验评估显示了提出的MMKDDA框架对其他流行基线的有效性,并且还进行了消融研究,以进一步分析每个组件在我们的框架中的作用。
translated by 谷歌翻译
持续学习的目标(CL)是随着时间的推移学习不同的任务。与CL相关的主要Desiderata是在旧任务上保持绩效,利用后者来改善未来任务的学习,并在培训过程中引入最小的开销(例如,不需要增长的模型或再培训)。我们建议通过固定密度的稀疏神经网络来解决这些避难所的神经启发性塑性适应(NISPA)体系结构。 NISPA形成了稳定的途径,可以从较旧的任务中保存知识。此外,NISPA使用连接重新设计来创建新的塑料路径,以重用有关新任务的现有知识。我们对EMNIST,FashionMnist,CIFAR10和CIFAR100数据集的广泛评估表明,NISPA的表现明显胜过代表性的最先进的持续学习基线,并且与盆地相比,它的可学习参数最多少了十倍。我们还认为稀疏是持续学习的重要组成部分。 NISPA代码可在https://github.com/burakgurbuz97/nispa上获得。
translated by 谷歌翻译
增量任务学习(ITL)是一个持续学习的类别,试图培训单个网络以进行多个任务(一个接一个),其中每个任务的培训数据仅在培训该任务期间可用。当神经网络接受较新的任务培训时,往往会忘记旧任务。该特性通常被称为灾难性遗忘。为了解决此问题,ITL方法使用情节内存,参数正则化,掩盖和修剪或可扩展的网络结构。在本文中,我们提出了一个基于低级别分解的新的增量任务学习框架。特别是,我们表示每一层的网络权重作为几个等级1矩阵的线性组合。为了更新新任务的网络,我们学习一个排名1(或低级别)矩阵,并将其添加到每一层的权重。我们还引入了一个其他选择器向量,该向量将不同的权重分配给对先前任务的低级矩阵。我们表明,就准确性和遗忘而言,我们的方法的表现比当前的最新方法更好。与基于情节的内存和基于面具的方法相比,我们的方法还提供了更好的内存效率。我们的代码将在https://github.com/csiplab/task-increment-rank-update.git上找到。
translated by 谷歌翻译
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.
translated by 谷歌翻译
用户生成的内容(UGC)的盲图质量评估(BIQA)遭受范围效应,表明在整体质量范围,平均意见评分(MOS)和预测的MOS(PMO)(PMO)上有很好的相关性;关注特定范围,相关性较低。范围效应的原因是,在较大范围内和狭窄范围内的预测偏差破坏了MOS和PMO之间的均匀性。为了解决这个问题,提出了一种新的方法,从粗粒度度量到细粒度的预测。首先,我们为粗粒度度量设计了排名和梯度损失。损失保持了PMOS和MOS之间的顺序和毕业生一致性,从而在较大范围内减少了预测的偏差。其次,我们提出多级公差损失以进行细粒度的预测。损失受到减少阈值的限制,以限制较窄和较窄范围的预测偏差。最后,我们设计了一个反馈网络来进行粗到精细的评估。一方面,网络采用反馈块来处理多尺度的失真功能,另一方面,它将非本地上下文功能融合到每次迭代的输出中,以获取更多质量感知的功能表示。实验结果表明,与最先进的方法相比,提出的方法可以减轻范围效应。
translated by 谷歌翻译
人的大脑能够依次地学习任务,而无需忘记。但是,深度神经网络(DNN)在学习一项任务时遭受灾难性遗忘。我们考虑了一个挑战,考虑了一个课堂学习方案,在该方案中,DNN看到测试数据而不知道该数据启动的任务。在培训期间,持续的捕获和选择(CP&S)在DNN中找到了负责解决给定任务的子网。然后,在推理期间,CP&S选择正确的子网以对该任务进行预测。通过培训DNN的可用神经元连接(以前未经训练)来创建一个新的子网络,从而通过修剪来学习一项新任务,该连接可以包括以前训练的其他子网络(S),因为它没有更新共享的连接,因为它可以属于其他子网络(S)。这使得通过在DNN中创建专门的区域而不会相互冲突的同时仍允许知识转移在其中,可以消除灾难性的遗忘。 CP&S策略采用不同的子网络选择策略实施,揭示了在各种数据集(CIFAR-100,CUB-200,2011年,Imagenet-100和Imagenet-100)上测试的最先进的持续学习方法的卓越性能。特别是,CP&S能够从Imagenet-1000中依次学习10个任务,以确保94%的精度,而遗忘可忽略不计,这是课堂学习学习的首要结果。据作者所知,与最佳替代方法相比,这表示准确性高于20%的改善。
translated by 谷歌翻译
由于空间分辨率的巨大改进,4K内容可以为消费者提供更严肃的视觉体验。但是,由于分辨率扩大和特定的扭曲,现有的盲图质量评估(BIQA)方法不适合原始和升级的4K内容物。在本文中,我们提出了一个针对4K内容的深度学习的BIQA模型,一方面可以识别True和pseudo 4K内容,另一方面可以评估其感知视觉质量。考虑到高空间分辨率可以代表更丰富的高频信息的特征,我们首先提出了基于灰色级别的共发生矩阵(GLCM)的纹理复杂度度量,以从4K图像中选择三个代表性图像贴片,这可以减少计算复杂性,被证明对通过实验的总体质量预测非常有效。然后,我们从卷积神经网络(CNN)的中间层中提取不同种类的视觉特征,并将它们集成到质量感知的特征表示中。最后,使用两个多层感知(MLP)网络用于将质量感知功能映射到类概率和每个贴片的质量分数中。总体质量指数是通过平均贴片结果汇总获得的。提出的模型通过多任务学习方式进行了训练,我们引入了不确定性原理,以平衡分类和回归任务的损失。实验结果表明,所提出的模型的表现均优于所有4K内容质量评估数据库中的BIQA指标。
translated by 谷歌翻译
Graph learning is a popular approach for performing machine learning on graph-structured data. It has revolutionized the machine learning ability to model graph data to address downstream tasks. Its application is wide due to the availability of graph data ranging from all types of networks to information systems. Most graph learning methods assume that the graph is static and its complete structure is known during training. This limits their applicability since they cannot be applied to problems where the underlying graph grows over time and/or new tasks emerge incrementally. Such applications require a lifelong learning approach that can learn the graph continuously and accommodate new information whilst retaining previously learned knowledge. Lifelong learning methods that enable continuous learning in regular domains like images and text cannot be directly applied to continuously evolving graph data, due to its irregular structure. As a result, graph lifelong learning is gaining attention from the research community. This survey paper provides a comprehensive overview of recent advancements in graph lifelong learning, including the categorization of existing methods, and the discussions of potential applications and open research problems.
translated by 谷歌翻译
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.
translated by 谷歌翻译
在本文中,我们提出了通过特征级伪参考(PR)幻觉提出的无引用(NR)图像质量评估(IQA)方法。提出的质量评估框架基于自然图像统计行为的先前模型,并植根于以下观点,即可以很好地利用具有感知意义的特征来表征视觉质量。本文中,通过以原始参考为监督的相互学习方案学习了扭曲的图像中的PR特征,并通过三重态约束进一步确保PR特征的区分特性。给定质量推断的扭曲图像,特征水平的分离是用可逆神经层进行最终质量预测的,导致PR和相应的失真特征以进行比较。在四个流行的IQA数据库中证明了我们提出的方法的有效性,跨数据库评估的卓越性能也揭示了我们方法的高概括能力。我们的方法的实现可在https://github.com/baoliang93/fpr上公开获得。
translated by 谷歌翻译
自然图像的统计规律(称为自然场景统计数据)在不引用图像质量评估中起重要作用。但是,人们普遍认为,通常是计算机生成的屏幕内容图像(SCI)不持有此类统计信息。在这里,我们首次尝试学习SCI的统计数据,基于可以有效确定SCI的质量。所提出的方法的基本机制是基于一个狂野的假设,即没有物理上获得的SCI仍然遵守某些可以以学习方式理解的统计数据。我们从经验上表明,在质量评估中可以有效利用统计偏差,并且在不同的环境中进行评估时,提出的方法优越。广泛的实验结果表明,与现有的NR-IQA模型相比,基于深度统计的SCI质量评估(DFSS-IQA)模型可提供有希望的性能,并在跨数据库设置中显示出很高的概括能力。我们的方法的实现可在https://github.com/baoliang93/dfss-iqa上公开获得。
translated by 谷歌翻译
Contemporary methods have shown promising results on cardiac image segmentation, but merely in static learning, i.e., optimizing the network once for all, ignoring potential needs for model updating. In real-world scenarios, new data continues to be gathered from multiple institutions over time and new demands keep growing to pursue more satisfying performance. The desired model should incrementally learn from each incoming dataset and progressively update with improved functionality as time goes by. As the datasets sequentially delivered from multiple sites are normally heterogenous with domain discrepancy, each updated model should not catastrophically forget previously learned domains while well generalizing to currently arrived domains or even unseen domains. In medical scenarios, this is particularly challenging as accessing or storing past data is commonly not allowed due to data privacy. To this end, we propose a novel domain-incremental learning framework to recover past domain inputs first and then regularly replay them during model optimization. Particularly, we first present a style-oriented replay module to enable structure-realistic and memory-efficient reproduction of past data, and then incorporate the replayed past data to jointly optimize the model with current data to alleviate catastrophic forgetting. During optimization, we additionally perform domain-sensitive feature whitening to suppress model's dependency on features that are sensitive to domain changes (e.g., domain-distinctive style features) to assist domain-invariant feature exploration and gradually improve the generalization performance of the network. We have extensively evaluated our approach with the M&Ms Dataset in single-domain and compound-domain incremental learning settings with improved performance over other comparison approaches.
translated by 谷歌翻译