很少有类别的课堂学习(FSCIL)旨在使用一些示例逐步微调模型(在基础课上培训),而不忘记先前的培训。最近的工作主要解决了2D图像。但是,由于相机技术的发展,3D点云数据比以往任何时候都更可用,这需要考虑3D数据的FSCIL。本文介绍了3D域中的FSCIL。除了灾难性忘记过去的知识和过度贴合数据的众所周知的问题外,3D FSCIL还可以带来更新的挑战。例如,基类可能在现实情况下包含许多合成实例。相比之下,新型类​​别只有少数几个实际扫描的样本(来自RGBD传感器)以增量步骤获得。由于数据从合成到真实的变化,FSCIL会承受其他挑战,以后的增量步骤降低了性能。我们尝试使用微莎普(正交基矢量)来解决此问题,并使用预定义的一组规则来描述任何3D对象。它支持逐步训练,几乎没有示例将合成与真实数据变化最小化。我们使用流行的合成数据集(ModelNet和Shapenet)和3D实范围的数据集(ScanoBjectNN和CO3D)为3D FSCIL提供新的测试协议。通过比较最先进的方法,我们确定了3D域中方法的有效性。
translated by 谷歌翻译
与其2D图像对应物相比,3D点云数据上的零射击学习是一个相关的未置换问题。 3D数据由于不可用的预训练特征提取模型而带来了ZSL的新挑战。为了解决这个问题,我们提出了一种及时引导的3D场景生成和监督方法,该方法可以增强3D数据以更好地学习网络,从而探索可见和看不见的对象的复杂相互作用。首先,我们以提示描述的某些方式合并了两个3D模型的点云。提示的行为就像描述每个3D场景的注释一样。后来,我们进行对比学习,以端到端的方式培训我们所提出的建筑。我们认为,与单​​个对象相比,3D场景可以更有效地关联对象,因为当对象出现在上下文中时,流行的语言模型(如Bert)可以实现高性能。我们提出的及时引导场景生成方法封装了数据扩展和基于及时的注释/字幕,以提高3D ZSL性能。我们已经在合成(ModelNet40,ModelNet10)和实扫描(ScanoJbectnn)3D对象数据集上实现了最新的ZSL和广义ZSL性能。
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
很少有图像分类是一个具有挑战性的问题,旨在仅基于少量培训图像来达到人类的识别水平。少数图像分类的一种主要解决方案是深度度量学习。这些方法是,通过将看不见的样本根据距离的距离进行分类,可在强大的深神经网络中学到的嵌入空间中看到的样品,可以避免以少数图像分类的少数训练图像过度拟合,并实现了最新的图像表现。在本文中,我们提供了对深度度量学习方法的最新审查,以进行2018年至2022年的少量图像分类,并根据度量学习的三个阶段将它们分为三组,即学习功能嵌入,学习课堂表示和学习距离措施。通过这种分类法,我们确定了他们面临的不同方法和问题的新颖性。我们通过讨论当前的挑战和未来趋势进行了少量图像分类的讨论。
translated by 谷歌翻译
大多数元学习方法都假设存在于可用于基本知识的情节元学习的一组非常大的标记数据。这与更现实的持续学习范例形成对比,其中数据以包含不相交类的任务的形式逐步到达。在本文中,我们考虑了这个增量元学习(IML)的这个问题,其中类在离散任务中逐步呈现。我们提出了一种方法,我们调用了IML,我们称之为eCISODIC重播蒸馏(ERD),该方法将来自当前任务的类混合到当前任务中,当研究剧集时,来自先前任务的类别示例。然后将这些剧集用于知识蒸馏以最大限度地减少灾难性的遗忘。四个数据集的实验表明ERD超越了最先进的。特别是,在一次挑战的单次次数较挑战,长任务序列增量元学习场景中,我们将IML和联合训练与当前状态的3.5%/ 10.1%/ 13.4%之间的差距降低我们在Diered-ImageNet / Mini-ImageNet / CIFAR100上分别为2.6%/ 2.9%/ 5.0%。
translated by 谷歌翻译
Many modern computer vision algorithms suffer from two major bottlenecks: scarcity of data and learning new tasks incrementally. While training the model with new batches of data the model looses it's ability to classify the previous data judiciously which is termed as catastrophic forgetting. Conventional methods have tried to mitigate catastrophic forgetting of the previously learned data while the training at the current session has been compromised. The state-of-the-art generative replay based approaches use complicated structures such as generative adversarial network (GAN) to deal with catastrophic forgetting. Additionally, training a GAN with few samples may lead to instability. In this work, we present a novel method to deal with these two major hurdles. Our method identifies a better embedding space with an improved contrasting loss to make classification more robust. Moreover, our approach is able to retain previously acquired knowledge in the embedding space even when trained with new classes. We update previous session class prototypes while training in such a way that it is able to represent the true class mean. This is of prime importance as our classification rule is based on the nearest class mean classification strategy. We have demonstrated our results by showing that the embedding space remains intact after training the model with new classes. We showed that our method preformed better than the existing state-of-the-art algorithms in terms of accuracy across different sessions.
translated by 谷歌翻译
基于草图的3D形状检索(SBSR)是一项重要但艰巨的任务,近年来引起了越来越多的关注。现有方法在限制设置中解决了该问题,而无需适当模拟真实的应用程序方案。为了模仿现实的设置,在此曲目中,我们采用了不同级别的绘图技能的业余爱好者以及各种3D形状的大规模草图,不仅包括CAD型号,而且还可以从真实对象扫描的模型。我们定义了两个SBSR任务,并构建了两个基准,包括46,000多个CAD型号,1,700个现实型号和145,000个草图。四个团队参加了这一轨道,并为这两个任务提交了15次跑步,由7个常用指标评估。我们希望,基准,比较结果和开源评估法会在3D对象检索社区中促进未来的研究。
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
很少有课堂学习(FSCIL)着重于设计学习算法,这些学习算法可以不断地从几个样本中学习一系列新任务,而不会忘记旧任务。困难是,从新任务中进行一系列有限数据的培训会导致严重的过度拟合问题,并导致众所周知的灾难性遗忘问题。现有研究主要利用图像信息,例如存储以前任务的图像知识或限制分类器更新。但是,他们忽略了分析课堂标签的信息丰富且较少的嘈杂文本信息。在这项工作中,我们建议通过采用内存提示来利用标签文本信息。内存提示可以依次学习新数据,同时存储先前的知识。此外,为了优化内存提示而不破坏存储的知识,我们提出了基于刺激的训练策略。它根据图像嵌入刺激(即嵌入元素的分布)来优化内存提示。实验表明,我们提出的方法的表现优于所有先前的最新方法,从而大大减轻了灾难性的遗忘和过度拟合问题。
translated by 谷歌翻译
虽然对2D图像的零射击学习(ZSL)进行了许多研究,但其在3D数据中的应用仍然是最近且稀缺的,只有几种方法限于分类。我们在3D数据上介绍了ZSL和广义ZSL(GZSL)的第一代生成方法,可以处理分类,并且是第一次语义分割。我们表明它达到或胜过了INTEMNET40对归纳ZSL和归纳GZSL的ModelNet40分类的最新状态。对于语义分割,我们创建了三个基准,用于评估此新ZSL任务,使用S3DIS,Scannet和Semantickitti进行评估。我们的实验表明,我们的方法优于强大的基线,我们另外为此任务提出。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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。
translated by 谷歌翻译
逐渐射击的语义分割(IFSS)目标以逐步扩展模型的能力逐渐扩大了仅由几个样本监督的新图像。但是,在旧课程中学到的特征可能会大大漂移,从而导致灾难性遗忘。此外,很少有针对新课程的像素级细分样本会导致每个学习课程中臭名昭著的过度拟合问题。在本文中,我们明确表示基于类别的语义分割的知识作为类别嵌入和超级类嵌入,前者描述了独家的语义属性,而后者则表示超级类知识作为类共享语义属性。为了解决IFSS问题,我们提出了EHNET,即从两个方面嵌入自适应更高和超级级表示网络。首先,我们提出了一种嵌入自适应的策略,以避免特征漂移,该策略通过超级班级表示保持旧知识,并使用类似课程的方案自适应地更新类别嵌入类别,以涉及在各个会话中学习的新课程。其次,为了抵制很少有培训样本引起的过度拟合问题,通过将所有类别嵌入以进行初始化并与新班级的类别保持一致以进行增强,从而学习了超级班级的嵌入,从而使学会知识有助于学习新知识,从而减轻了绩效绩效的绩效,依赖培训数据量表。值得注意的是,这两种设计为具有足够语义和有限偏见的类提供了表示能力,从而可以执行需要高语义依赖性的分割任务。 Pascal-5i和可可数据集的实验表明,EHNET具有显着优势的新最先进的性能。
translated by 谷歌翻译
在本文中,我们将3D点云的古典表示作为线性形状模型。我们的主要洞察力是利用深度学习,代表一种形状的集合,作为低维线性形状模型的仿射变换。每个线性模型的特征在于形状原型,低维形状基础和两个神经网络。网络以输入点云作为输入,并在线性基础中预测形状的坐标和最能近似输入的仿射变换。使用单一的重建损耗来学习线性模型和神经网络的结束。我们方法的主要优点是,与近期学习基于特征的复杂形状表示的许多深度方法相比,我们的模型是显式的,并且在3D空间中发生每个操作。结果,我们的线性形状模型可以很容易地可视化和注释,并且可以在视觉上了解故障情况。虽然我们的主要目标是引入紧凑且可解释的形状收集表示,但我们表明它导致最新的最先进结果对几次射击分割。
translated by 谷歌翻译
深度神经网络在学习新任务时遭受灾难性遗忘的主要限制。在本文中,我们专注于语义细分中的课堂持续学习,其中新类别随着时间的推移,而在未保留以前的训练数据。建议的持续学习方案塑造了潜在的空间来减少遗忘,同时提高了对新型课程的识别。我们的框架是由三种新的组件驱动,我们还毫不费力地结合现有的技术。首先,匹配的原型匹配在旧类上强制执行潜在空间一致性,约束编码器在后续步骤中为先前看到的类生成类似的潜在潜在表示。其次,特征稀疏性允许在潜在空间中腾出空间以容纳新型课程。最后,根据他们的语义,在统一的同时撕裂不同类别的语义,对形成对比的学习。对Pascal VOC2012和ADE20K数据集的广泛评估展示了我们方法的有效性,显着优于最先进的方法。
translated by 谷歌翻译
很少有课堂学习(FSCIL)旨在仅用几个样本不断学习新概念,这很容易遭受灾难性的遗忘和过度拟合的问题。旧阶级的无法获得性和新颖样本的稀缺性使实现保留旧知识和学习新颖概念之间的权衡很大。受到不同模型的启发,我们在学习新颖概念时记住了不同的知识,我们提出了一个记忆的补充网络(MCNET),以整合多个模型,以在新任务中相互补充不同的记忆知识。此外,为了用很少的新样本更新模型,我们开发了一个原型平滑的硬矿三元组(PSHT)损失,以将新型样品不仅在当前任务中彼此远离,而且在旧分布中脱颖而出。在三个基准数据集(例如CIFAR100,Miniimagenet和Cub200)上进行了广泛的实验,证明了我们提出的方法的优势。
translated by 谷歌翻译
The counting task, which plays a fundamental rule in numerous applications (e.g., crowd counting, traffic statistics), aims to predict the number of objects with various densities. Existing object counting tasks are designed for a single object class. However, it is inevitable to encounter newly coming data with new classes in our real world. We name this scenario as \textit{evolving object counting}. In this paper, we build the first evolving object counting dataset and propose a unified object counting network as the first attempt to address this task. The proposed model consists of two key components: a class-agnostic mask module and a class-increment module. The class-agnostic mask module learns generic object occupation prior via predicting a class-agnostic binary mask (e.g., 1 denotes there exists an object at the considering position in an image and 0 otherwise). The class-increment module is used to handle new coming classes and provides discriminative class guidance for density map prediction. The combined outputs of class-agnostic mask module and image feature extractor are used to predict the final density map. When new classes come, we first add new neural nodes into the last regression and classification layers of this module. Then, instead of retraining the model from scratch, we utilize knowledge distilling to help the model remember what have already learned about previous object classes. We also employ a support sample bank to store a small number of typical training samples of each class, which are used to prevent the model from forgetting key information of old data. With this design, our model can efficiently and effectively adapt to new coming classes while keeping good performance on already seen data without large-scale retraining. Extensive experiments on the collected dataset demonstrate the favorable performance.
translated by 谷歌翻译
广义零射击学习(GZSL)旨在培训一个模型,以在某些输出类别在监督学习过程中未知的情况下对数据样本进行分类。为了解决这一具有挑战性的任务,GZSL利用可见的(源)和看不见的(目标)类的语义信息来弥合所见类和看不见的类之间的差距。自引入以来,已经制定了许多GZSL模型。在这篇评论论文中,我们介绍了有关GZSL的全面评论。首先,我们提供了GZSL的概述,包括问题和挑战。然后,我们为GZSL方法介绍了分层分类,并讨论了每个类别中的代表性方法。此外,我们讨论了GZSL的可用基准数据集和应用程序,以及有关研究差距和未来研究方向的讨论。
translated by 谷歌翻译
新课程经常出现在我们不断变化的世界中,例如社交媒体中的新兴主题和电子商务中的新产品。模型应识别新的类,同时保持对旧类的可区分性。在严重的情况下,只有有限的新颖实例可以逐步更新模型。在不忘记旧课程的情况下识别几个新课程的任务称为少数类的课程学习(FSCIL)。在这项工作中,我们通过学习多相增量任务(limit)提出了一个基于元学习的FSCIL的新范式,该任务从基本数据集中综合了伪造的FSCIL任务。假任务的数据格式与“真实”的增量任务一致,我们可以通过元学习构建可概括的特征空间。此外,限制还基于变压器构建了一个校准模块,该模块将旧类分类器和新类原型校准为相同的比例,并填补语义间隙。校准模块还可以自适应地将具有设置对集合函数的特定于实例的嵌入方式化。限制有效地适应新课程,同时拒绝忘记旧课程。在三个基准数据集(CIFAR100,Miniimagenet和Cub200)和大规模数据集上进行的实验,即Imagenet ILSVRC2012验证以实现最新性能。
translated by 谷歌翻译
Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used to solve various 2D vision problems. However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks. Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area. To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds. It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation. It also presents comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions.
translated by 谷歌翻译