The booming development and huge market of micro-videos bring new e-commerce channels for merchants. Currently, more micro-video publishers prefer to embed relevant ads into their micro-videos, which not only provides them with business income but helps the audiences to discover their interesting products. However, due to the micro-video recording by unprofessional equipment, involving various topics and including multiple modalities, it is challenging to locate the products related to micro-videos efficiently, appropriately, and accurately. We formulate the microvideo-product retrieval task, which is the first attempt to explore the retrieval between the multi-modal and multi-modal instances. A novel approach named Multi-Queue Momentum Contrast (MQMC) network is proposed for bidirectional retrieval, consisting of the uni-modal feature and multi-modal instance representation learning. Moreover, a discriminative selection strategy with a multi-queue is used to distinguish the importance of different negatives based on their categories. We collect two large-scale microvideo-product datasets (MVS and MVS-large) for evaluation and manually construct the hierarchical category ontology, which covers sundry products in daily life. Extensive experiments show that MQMC outperforms the state-of-the-art baselines. Our replication package (including code, dataset, etc.) is publicly available at https://github.com/duyali2000/MQMC.
translated by 谷歌翻译
Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images. However, delineating vectorized and regular building contours like a human does remains very challenging, due to the difficulty of the methodology, the diversity of building structures, and the imperfect imaging conditions. In this paper, we propose the first end-to-end learnable building contour extraction framework, named BuildMapper, which can directly and efficiently delineate building polygons just as a human does. BuildMapper consists of two main components: 1) a contour initialization module that generates initial building contours; and 2) a contour evolution module that performs both contour vertex deformation and reduction, which removes the need for complex empirical post-processing used in existing methods. In both components, we provide new ideas, including a learnable contour initialization method to replace the empirical methods, dynamic predicted and ground truth vertex pairing for the static vertex correspondence problem, and a lightweight encoder for vertex information extraction and aggregation, which benefit a general contour-based method; and a well-designed vertex classification head for building corner vertices detection, which casts light on direct structured building contour extraction. We also built a suitable large-scale building dataset, the WHU-Mix (vector) building dataset, to benefit the study of contour-based building extraction methods. The extensive experiments conducted on the WHU-Mix (vector) dataset, the WHU dataset, and the CrowdAI dataset verified that BuildMapper can achieve a state-of-the-art performance, with a higher mask average precision (AP) and boundary AP than both segmentation-based and contour-based methods.
translated by 谷歌翻译
Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.
translated by 谷歌翻译
在本文中,我们介绍了一个新的建筑数据集,并提出了一种新颖的域泛化方法,以促进从高分辨率遥感图像中提取建筑物的开发。当前建筑数据集的问题涉及它们缺乏多样性,标签的质量不令人满意,并且几乎不用于培训具有良好概括能力的建筑提取模型,以便正确地评估模型在实践中的真实性能场景。为了解决这些问题,我们建立了一个名为WHU-MIX建筑数据集的多样化,大规模和高质量的建筑数据集,该数据集更加面向实践。 WHU-MIX建筑物数据集由一个培训/验证集组成,该培训/验证集包含来自世界各地的43,727个不同图像,以及一个测试集,其中包含来自五大洲其他五个城市的8402张图像。此外,为了进一步提高建筑物提取模型的概括能力,我们提出了一种名为批处理样式混合(BSM)的域概括方法,该方法可以嵌入建筑物的frond-end中,以嵌入为有效的插件模块提取模型,为模型提供逐渐更大的数据分布,以学习数据不变知识。这项研究中进行的实验证实了WHU-MIX建筑数据集的潜力,以提高建筑物提取模型的性能,与其他现有数据集相比,MIOU提高了6-36%。其他数据集中标签不准确的不利影响可能会导致约20%的IOU减少。该实验还证实了所提出的BSM模块在增强模型的概括能力和鲁棒性方面的高性能,超过了13%的基线模型,而MIOU中最新的域概括方法则超过了4-15%。
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
尽管近年来从CT/MRI扫描中自动腹部多器官分割取得了很大进展,但由于缺乏各种临床方案的大规模基准,对模型的能力的全面评估受到阻碍。收集和标记3D医学数据的高成本的限制,迄今为止的大多数深度学习模型都由具有有限数量的感兴趣或样品器官的数据集驱动,这仍然限制了现代深层模型的力量提供各种方法的全面且公平的估计。为了减轻局限性,我们提出了AMO,这是一个大规模,多样的临床数据集,用于腹部器官分割。 AMOS提供了从多中心,多供应商,多模式,多相,多疾病患者收集的500 CT和100次MRI扫描,每个患者均具有15个腹部器官的体素级注释,提供了具有挑战性的例子,并提供了挑战性的例子和测试结果。在不同的目标和场景下研究健壮的分割算法。我们进一步基准了几种最先进的医疗细分模型,以评估此新挑战性数据集中现有方法的状态。我们已公开提供数据集,基准服务器和基线,并希望激发未来的研究。信息可以在https://amos22.grand-challenge.org上找到。
translated by 谷歌翻译
通过强迫连续重量的最多n非零,最近的N:M网络稀疏性因其两个有吸引力的优势而受到越来越多的关注:1)高稀疏性的有希望的表现。 2)对NVIDIA A100 GPU的显着加速。最近的研究需要昂贵的训练阶段或重型梯度计算。在本文中,我们表明N:M学习可以自然地将其描述为一个组合问题,该问题可以在有限的集合中寻找最佳组合候选者。由这种特征激励,我们以有效的分裂方式解决了n:m的稀疏性。首先,我们将重量向量分为$ c _ {\ text {m}}}^{\ text {n}} $组合s子集的固定大小N。然后,我们通过分配每个组合来征服组合问题,一个可学习的分数是共同优化了其关联权重。我们证明,引入的评分机制可以很好地模拟组合子集之间的相对重要性。通过逐渐去除低得分的子集,可以在正常训练阶段有效地优化N:M细粒稀疏性。全面的实验表明,我们的学习最佳组合(LBC)的表现始终如一,始终如一地比现成的N:m稀疏方法更好。我们的代码在\ url {https://github.com/zyxxmu/lbc}上发布。
translated by 谷歌翻译
在本文中,我们提出了一个简单而通用的网络,该网络称为SEQTR,用于视觉接地任务,例如短语本地化,参考表达理解(REC)和分割(RES)。视觉接地的规范范例通常需要在设计网络体系结构和损失功能方面具有丰富的专业知识,从而使它们难以跨越跨任务进行推广。为了简化和统一建模,我们将视觉接地作为点预测问题在图像和文本输入上进行条件,其中边界框或二进制掩码表示为一系列离散坐标令牌。在此范式下,视觉接地任务是在我们的SEQTR网络中统一的,而没有特定于任务的分支或头部,例如RES的卷积蒙版解码器,这大大降低了多任务建模的复杂性。此外,SEQTR还具有简单的交叉渗透损失,共享所有任务的相同优化目标,从而进一步降低了部署手工制作的损失功能的复杂性。五个基准数据集的实验表明,所提出的SEQTR优于现有的最新技术(或与之相提并论),这证明了一种简单而通用的视觉接地方法确实是可行的。源代码可在https://github.com/sean-zhuh/seqtr上获得。
translated by 谷歌翻译
本文报告了Chalearn的Autodl挑战系列的结果和后攻击分析,这有助于对自动学习(DL)进行分类,以便在各种环境中引入的深度学习(DL),但缺乏公平的比较。格式化所有输入数据模型(时间序列,图像,视频,文本,表格)作为张量,所有任务都是多标签分类问题。代码提交已在隐藏的任务上执行,具有限制时间和计算资源,推动快速获取结果的解决方案。在此设置中,DL方法占主导地位,但流行的神经结构搜索(NAS)是不切实际的。解决方案依赖于微调预培训的网络,架构匹配数据模块。挑战后测试没有透露超出强加时间限制的改进。虽然没有组件尤其原始或新颖,但是一个高级模块化组织出现了“Meta-Learner”,“数据摄入”,“模型选择器”,“模型/学习者”和“评估员”。这种模块化使得消融研究,揭示了(离坡)元学习,合奏和高效数据管理的重要性。异构模块组合的实验进一步证实了获胜解决方案的(本地)最优性。我们的挑战队遗产包括一个持久的基准(http://utodl.chalearn.org),获胜者的开放源代码,以及免费的“autodl自助服务”。
translated by 谷歌翻译
恶意软件是跨越多个操作系统和各种文件格式的计算机的最损害威胁之一。为了防止不断增长的恶意软件的威胁,已经提出了巨大的努力来提出各种恶意软件检测方法,试图有效和有效地检测恶意软件。最近的研究表明,一方面,现有的ML和DL能够卓越地检测新出现和以前看不见的恶意软件。然而,另一方面,ML和DL模型本质上易于侵犯对抗性示例形式的对抗性攻击,这通过略微仔细地扰乱了合法输入来混淆目标模型来恶意地产生。基本上,在计算机视觉领域最初广泛地研究了对抗性攻击,并且一些快速扩展到其他域,包括NLP,语音识别甚至恶意软件检测。在本文中,我们专注于Windows操作系统系列中的便携式可执行文件(PE)文件格式的恶意软件,即Windows PE恶意软件,作为在这种对抗设置中研究对抗性攻击方法的代表性案例。具体而言,我们首先首先概述基于ML / DL的Windows PE恶意软件检测的一般学习框架,随后突出了在PE恶意软件的上下文中执行对抗性攻击的三个独特挑战。然后,我们进行全面和系统的审查,以对PE恶意软件检测以及增加PE恶意软件检测的稳健性的相应防御,对近最新的对手攻击进行分类。我们首先向Windows PE恶意软件检测的其他相关攻击结束除了对抗对抗攻击之外,然后对未来的研究方向和机遇脱落。
translated by 谷歌翻译