基于草图的图像检索(SBIR)是检索与语义和手绘草图查询的空间配置相匹配的自然图像(照片)的任务。草图的普遍性扩大了可能的应用程序的范围,并增加了对有效SBIR解决方案的需求。在本文中,我们研究了经典的基于三胞胎的SBIR解决方案,并表明对水平翻转(即使在模型登录之后)的持续不变性也损害了性能。为了克服这一限制,我们提出了几种方法,并深入评估它们每个方法以检查其有效性。我们的主要贡献是双重的:我们提出并评估几种直观的修改,以构建具有更好的翻转均衡性的SBIR解决方案。我们表明,视觉变压器更适合SBIR任务,并且它们的优于CNN的优于较大的CNN。我们进行了许多实验,并引入了第一个模型,以优于大规模SBIR基准(粗略)的人类表现。与以前的最新方法相比,我们的最佳模型在粗略的基准测试中达到了62.25%(在k = 1)的召回率为46.2%。
translated by 谷歌翻译
本文从跨模式度量学习的角度来解决基于零点草图的图像检索(ZS-SBIR)问题。此任务具有两个特性:1)零拍摄设置需要具有良好的课堂紧凑性和识别新颖类别的课堂间差异的度量空间,而2)草图查询和照片库是不同的模态。从两个方面,公制学习视点益处ZS-SBIR。首先,它促进了深度度量学习(DML)中最近的良好实践的改进。通过在DML中结合两种基本学习方法,例如分类培训和成对培训,我们为ZS-SBIR设置了一个强大的基线。没有钟声和口哨,这种基线实现了竞争的检索准确性。其次,它提供了一个正确抑制模态间隙至关重要的洞察力。为此,我们设计了一种名为Domency Ippar Triplet硬挖掘(Mathm)的新颖方法。 Mathm增强了基线,具有三种类型的成对学习,例如跨模型样本对,模态样本对,以及它们的组合。\我们还设计了一种自适应加权方法,可以在动态训练期间平衡这三个组件。实验结果证实,Mathm根据强大的基线带来另一轮显着改进,并建立了新的最先进的性能。例如,在Tu-Berlin数据集上,我们达到了47.88 + 2.94%地图@全部和58.28 + 2.34%prip @ 100。代码将在:https://github.com/huangzongheng/mathm公开使用。
translated by 谷歌翻译
基于细粒的草图的图像检索(FG-SBIR)解决了在给定查询草图中检索特定照片的问题。然而,它的广泛适用性受到大多数人为大多数人绘制完整草图的事实的限制,并且绘图过程经常需要时间。在这项研究中,我们的目标是用最少数量的笔划检索目标照片(不完整草图),命名为vs-the-fry fg-sbir(bhunia等人.2020),它一旦尽快开始检索每个行程绘图开始。我们认为每张照片的草图绘图集中的这些不完整草图之间存在显着相关性。为了了解照片和ITS不完整的草图之间共享的更高效的联合嵌入空间,我们提出了一个多粒度关联学习框架,进一步优化了所有不完整草图的嵌入空间。具体地,基于草图的完整性,我们可以将完整的草图插曲分为几个阶段,每个阶段对应于简单的线性映射层。此外,我们的框架指导了当前草图的矢量空间表示,以近似速写,以实现草图的检索性能,以利用更多的笔触来接近草图的草图。在实验中,我们提出了更现实的挑战,我们的方法在两个公开的细粒草图检索数据集上实现了最先进的方法和替代基线的卓越的早期检索效率。
translated by 谷歌翻译
最近对基于细粒的基于草图的图像检索(FG-SBIR)的重点已转向将模型概括为新类别,而没有任何培训数据。但是,在现实世界中,经过训练的FG-SBIR模型通常应用于新类别和不同的人类素描器,即不同的绘图样式。尽管这使概括问题复杂化,但幸运的是,通常可以使用一些示例,从而使模型适应新的类别/样式。在本文中,我们提供了一种新颖的视角 - 我们没有要求使用概括的模型,而是提倡快速适应的模型,在测试过程中只有很少的样本(以几种方式)。为了解决这个新问题,我们介绍了一种基于几个关键修改的基于新型的模型 - 静态元学习(MAML)框架:(1)作为基于边缘的对比度损失的检索任务,我们简化了内部循环中的MAML训练使其更稳定和易于处理。 (2)我们的对比度损失的边距也通过其余模型进行了元学习。 (3)在外循环中引入了另外三个正规化损失,以使元学习的FG-SBIR模型对类别/样式适应更有效。在公共数据集上进行的广泛实验表明,基于概括和基于零射的方法的增益很大,还有一些强大的射击基线。
translated by 谷歌翻译
素描是一种常用于创新过程的自然和有效的视觉通信介质。深度学习模型的最新发展急剧改善了理解和生成视觉内容的机器能力。令人兴奋的发展领域探讨了用于模拟人类草图的深度学习方法,开设创造性应用的机会。本章介绍了开发深受学习驱动的创造性支持工具的三个基本步骤,这些步骤消耗和生成草图:1)在草图和移动用户界面之间生成新配对数据集的数据收集工作; 2)基于草图的用户界面检索系统,适用于最先进的计算机视觉技术; 3)一个对话的草图系统,支持基于自然语言的草图/批判创作过程的新颖互动。在本章中,我们在深度学习和人机互动社区中进行了对相关的事先工作,详细记录了数据收集过程和系统的架构,目前提供了定性和定量结果,并绘制了几个未来研究的景观在这个令人兴奋的地区的方向。
translated by 谷歌翻译
细粒度的图像分析(FGIA)是计算机视觉和模式识别中的长期和基本问题,并为一组多种现实世界应用提供了基础。 FGIA的任务是从属类别分析视觉物体,例如汽车或汽车型号的种类。细粒度分析中固有的小阶级和阶级阶级内变异使其成为一个具有挑战性的问题。利用深度学习的进步,近年来,我们在深入学习动力的FGIA中见证了显着进展。在本文中,我们对这些进展的系统进行了系统的调查,我们试图通过巩固两个基本的细粒度研究领域 - 细粒度的图像识别和细粒度的图像检索来重新定义和扩大FGIA领域。此外,我们还审查了FGIA的其他关键问题,例如公开可用的基准数据集和相关域的特定于应用程序。我们通过突出几个研究方向和开放问题,从社区中突出了几个研究方向和开放问题。
translated by 谷歌翻译
学习遥感(RS)图像之间的相似性形成基于内容的RS图像检索(CBIR)的基础。最近,将图像的语义相似性映射到嵌入(度量标准)空间的深度度量学习方法已经发现非常流行。学习公制空间的常见方法依赖于将与作为锚称为锚的参考图像的类似(正)和不同(负)图像的三胞胎的选择。选择三胞胎是一个难以为多标签RS CBIR的困难任务,其中每个训练图像由多个类标签注释。为了解决这个问题,在本文中,我们提出了一种在为多标签RS CBIR问题定义的深神经网络(DNN)的框架中提出了一种新颖的三联样品采样方法。该方法基于两个主要步骤选择一小部分最多代表性和信息性三元组。在第一步中,使用迭代算法从当前迷你批量选择在嵌入空间中彼此多样化的一组锚。在第二步中,通过基于新颖的策略评估彼此之间的图像的相关性,硬度和多样性来选择不同的正面和负图像。在两个多标签基准档案上获得的实验结果表明,在DNN的上下文中选择最具信息丰富和代表性的三胞胎,导致:i)降低DNN训练阶段的计算复杂性,而性能没有任何显着损失; ii)由于信息性三元组允许快速收敛,因此学习速度的增加。所提出的方法的代码在https://git.tu-berlin.de/rsim/image-reetrieval-from-tropls上公开使用。
translated by 谷歌翻译
Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade with promising results in various applications. The success of a DML algorithm greatly depends on its loss function. However, no loss function is perfect, and it deals only with some aspects of an optimal similarity embedding. Besides, the generalizability of the DML on unseen categories during the test stage is an important matter that is not considered by existing loss functions. To address these challenges, we propose novel approaches to combine different losses built on top of a shared deep feature extractor. The proposed ensemble of losses enforces the deep model to extract features that are consistent with all losses. Since the selected losses are diverse and each emphasizes different aspects of an optimal semantic embedding, our effective combining methods yield a considerable improvement over any individual loss and generalize well on unseen categories. Here, there is no limitation in choosing loss functions, and our methods can work with any set of existing ones. Besides, they can optimize each loss function as well as its weight in an end-to-end paradigm with no need to adjust any hyper-parameter. We evaluate our methods on some popular datasets from the machine vision domain in conventional Zero-Shot-Learning (ZSL) settings. The results are very encouraging and show that our methods outperform all baseline losses by a large margin in all datasets.
translated by 谷歌翻译
Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant in image retrieval due to their discriminative power, compactness of representation, and search efficiency. Training of CNNs, either from scratch or fine-tuning, requires a large amount of annotated data, where a high quality of annotation is often crucial. In this work, we propose to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner. Reconstructed 3D models obtained by the state-of-the-art retrieval and structure-from-motion methods guide the selection of the training data. We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval. CNN descriptor whitening discriminatively learned from the same training data outperforms commonly used PCA whitening. We propose a novel trainable Generalized-Mean (GeM) pooling layer that generalizes max and average pooling and show that it boosts retrieval performance. Applying the proposed method to the VGG network achieves state-of-the-art performance on the standard benchmarks: Oxford Buildings, Paris, and Holidays datasets.
translated by 谷歌翻译
草图和照片之间的巨大领域差距以及高度抽象的草图表示构成了基于草图的图像检索(\下划线{Sbir})的挑战。基于零拍的草图的图像检索(\下划线{ZS-SBIR})更通用,实用,但由于所看到和未遵守的类别之间的额外知识差距,造成更大的挑战。要同时缓解两个间隙,我们提出了一个\ textbf {a} pproaching-and-\ textbf {c}映射\ textbf {net}工作(称为`\ textbf {acnet}''),以共同优化素描到照片合成与图像检索。检索模块引导综合模块生成大量不同的光相似图像,该图像逐渐接近照片域,从而更好地服务于检索模块,而不是以前学习域名不可知的表征和类别 - 无名的共同知识,以概括到未经证明的类别。通过检索引导产生的这些不同的图像可以有效地减轻了高梯度的混凝土类别训练样本的过度装备问题。我们还发现使用基于代理的NormsoftMax丢失是有效的,因为它的集中效果可以稳定我们的联合培训并促进未经看管分类的概括能力。我们的方法简单而且有效,这在两个广泛使用的ZS-SBIR数据集上实现了最先进的性能,并通过大边距超过以前的方法。
translated by 谷歌翻译
近年来,已经产生了大量的视觉内容,并从许多领域共享,例如社交媒体平台,医学成像和机器人。这种丰富的内容创建和共享引入了新的挑战,特别是在寻找类似内容内容的图像检索(CBIR)-A的数据库中,即长期建立的研究区域,其中需要改进的效率和准确性来实时检索。人工智能在CBIR中取得了进展,并大大促进了实例搜索过程。在本调查中,我们审查了最近基于深度学习算法和技术开发的实例检索工作,通过深网络架构类型,深度功能,功能嵌入方法以及网络微调策略组织了调查。我们的调查考虑了各种各样的最新方法,在那里,我们识别里程碑工作,揭示各种方法之间的联系,并呈现常用的基准,评估结果,共同挑战,并提出未来的未来方向。
translated by 谷歌翻译
很少有细粒度的分类和人搜索作为独特的任务和文学作品,已经分别对待了它们。但是,仔细观察揭示了重要的相似之处:这两个任务的目标类别只能由特定的对象细节歧视;相关模型应概括为新类别,而在培训期间看不到。我们提出了一个适用于这两个任务的新型统一查询引导网络(QGN)。QGN由一个查询引导的暹罗引文和兴奋子网组成,该子网还重新进行了所有网络层的查询和画廊功能,一个查询实习的区域建议特定于特定于特定的本地化以及查询指导的相似性子网络子网本网络用于公制学习。QGN在最近的一些少数细颗粒数据集上有所改善,在幼崽上的其他技术优于大幅度。QGN还对人搜索Cuhk-Sysu和PRW数据集进行了竞争性执行,我们在其中进行了深入的分析。
translated by 谷歌翻译
学习模态不变功能是可见热跨模板人员重新凝视(VT-REID)问题的核心,其中查询和画廊图像来自不同的模式。现有工作通过使用对抗性学习或仔细设计特征提取模块来隐式地将像素和特征空间中的模态对齐。我们提出了一个简单但有效的框架MMD-REID,通过明确的差异减少约束来降低模态差距。 MMD-REID从最大均值(MMD)中获取灵感,广泛使用的统计工具用于确定两个分布之间的距离。 MMD-REID采用新的基于边缘的配方,以匹配可见和热样品的类条件特征分布,以最大限度地减少级别的距离,同时保持特征辨别性。 MMD-Reid是一个简单的架构和损失制定方面的框架。我们对MMD-REID的有效性进行了广泛的实验,以使MMD-REID对调整边缘和阶级条件分布的有效性,从而学习模型无关和身份的一致特征。所提出的框架显着优于Sysu-MM01和RegDB数据集的最先进的方法。代码将在https://github.com/vcl-iisc/mmd -reid发布
translated by 谷歌翻译
在本文中,我们提出了一种强大的样本生成方案来构建信息性三联网。所提出的硬样品生成是一种两级合成框架,通过两个阶段的有效正和负样品发生器产生硬样品。第一阶段将锚定向对具有分段线性操作,通过巧妙地设计条件生成的对抗网络来提高产生的样本的质量,以降低模式崩溃的风险。第二阶段利用自适应反向度量约束来生成最终的硬样本。在几个基准数据集上进行广泛的实验,验证了我们的方法比现有的硬样生成算法达到卓越的性能。此外,我们还发现,我们建议的硬样品生成方法结合现有的三态挖掘策略可以进一步提高深度度量学习性能。
translated by 谷歌翻译
Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on twelve datasets for FOUR different Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for real applications. Finally, some important yet under-investigated open issues are discussed.
translated by 谷歌翻译
The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios with large variances. In this paper, we propose an end-to-end feature learning strategy integrating discriminative information with various granularities. We carefully design the Multiple Granularity Network (MGN), a multi-branch deep network architecture consisting of one branch for global feature representations and two branches for local feature representations. Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities. Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that our method robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin. For example, on Market-1501 dataset in single query mode, we obtain a top result of Rank-1/mAP=96.6%/94.2% with this method after re-ranking.
translated by 谷歌翻译
本文的重点是具有属性操作的图像检索问题。我们所提出的工作能够在维护其它属性时操纵查询图像的所需属性。例如,查询图像的套环属性可以从圆形到V-N颈改变,以从大型数据集中检索类似的图像。电子商务中的一个关键挑战是图像具有多个属性,用户希望操纵,并且重要的是估计每个属性的判别特征表示。所提出的fashionsearchnet-v2架构能够通过利用其弱监管的本地化模块来学习属性特定表示,该模块忽略了特征空间中属性的不相关特征,从而提高了相似度学习。网络与属性分类和三联排名损失的组合进行了联合培训,以估计本地表示。然后,基于所指的属性操纵,这些本地表示被合并成单个全局表示,其中可以通过距离度量来检索期望的图像。该方法还提供了可解释性,以帮助提供有关网络注意的额外信息。在几个数据集上执行的实验,该数据集在属性的数量方面表明FashionSearchNet-V2优于其他最先进的属性操作技术。与我们之前的工作(FashionsearchNet)不同,我们提出了几种改进了学习程序,并表明所提出的FashionsearchNet-V2可以概括为除了时尚之外的不同域。
translated by 谷歌翻译
视觉变换器(VTS)作为卷积网络(CNNS)的架构范式替代品。与CNN不同,VT可以捕获图像元素之间的全局关系,并且它们可能具有更大的表示容量。然而,缺乏典型的卷积电感偏差使这些模型比普通的CNN更饥饿。实际上,嵌入在CNN架构设计中的某些本地属性,在VTS中应该从样品中学习。在本文中,我们明确地分析了不同的VTS,比较了他们在小型训练制度中的鲁棒性,并且我们表明,尽管在想象中训练时具有可比的准确性,但它们在较小数据集上的性能可能很大程度上不同。此外,我们提出了一种自我监督的任务,可以从图像中提取其他信息,只有可忽略不计的计算开销。这项任务鼓励VTS学习图像内的空间关系,并使VT培训在训练数据稀缺时更加强劲。我们的任务与标准(监督)培训共同使用,它不依赖于特定的架构选择,因此它可以轻松插入现有的VTS。使用与不同的VTS和数据集进行广泛的评估,我们表明我们的方法可以改善(有时显着地)VTS的最终精度。我们的代码可用于:https://github.com/yhlleo/vts-droc。
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
Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision.
translated by 谷歌翻译