Local feature detection is a key ingredient of many image processing and computer vision applications, such as visual odometry and localization. Most existing algorithms focus on feature detection from a sharp image. They would thus have degraded performance once the image is blurred, which could happen easily under low-lighting conditions. To address this issue, we propose a simple yet both efficient and effective keypoint detection method that is able to accurately localize the salient keypoints in a blurred image. Our method takes advantages of a novel multi-layer perceptron (MLP) based architecture that significantly improve the detection repeatability for a blurred image. The network is also light-weight and able to run in real-time, which enables its deployment for time-constrained applications. Extensive experimental results demonstrate that our detector is able to improve the detection repeatability with blurred images, while keeping comparable performance as existing state-of-the-art detectors for sharp images.
translated by 谷歌翻译
引用视频对象细分旨在分割给定语言表达式所引用的对象。现有作品通常需要压缩视频bitstream在分割之前将其解码为RGB帧,从而增加了计算和存储要求,并最终减慢了推断。这可能会妨碍其在现实世界计算资源有限的场景中的应用,例如自动驾驶汽车和无人机。为了减轻此问题,在本文中,我们探讨了压缩视频的引用对象细分任务,即原始视频数据流。除了视频引用对象分割任务本身的固有难度外,从压缩视频中获得歧视性表示也很具有挑战性。为了解决这个问题,我们提出了一个多发网络,该网络由双路线双注意模块和一个基于查询的跨模式变压器模块组成。具体而言,双路线双意见模块旨在从三种模态的压缩数据中提取有效表示,即i框架,运动矢量和残留。基于查询的跨模式变压器首先对语言和视觉方式之间的相关性进行建模,然后使用融合的多模式特征来指导对象查询以生成内容感知的动态内核并预测最终的分割掩码。与以前的作品不同,我们建议只学习一个内核,因此,它可以删除现有方法的复杂后掩模匹配程序。在三个具有挑战性的数据集上进行的广泛有希望的实验结果表明,与几种用于处理RGB数据的最新方法相比,我们的方法的有效性。源代码可在以下网址获得:https://github.com/dexianghong/manet。
translated by 谷歌翻译
多年来,使用单点监督的对象检测受到了越来越多的关注。在本文中,我们将如此巨大的性能差距归因于产生高质量的提案袋的失败,这对于多个实例学习至关重要(MIL)。为了解决这个问题,我们引入了现成建议方法(OTSP)方法的轻量级替代方案,从而创建点对点网络(P2BNET),该网络可以通过在中生成建议袋来构建一个互平衡的提案袋一种锚点。通过充分研究准确的位置信息,P2BNET进一步构建了一个实例级袋,避免了多个物体的混合物。最后,以级联方式进行的粗到精细政策用于改善提案和地面真相(GT)之间的IOU。从这些策略中受益,P2BNET能够生产出高质量的实例级袋以进行对象检测。相对于MS可可数据集中的先前最佳PSOD方法,P2BNET将平均平均精度(AP)提高了50%以上。它还证明了弥合监督和边界盒监督检测器之间的性能差距的巨大潜力。该代码将在github.com/ucas-vg/p2bnet上发布。
translated by 谷歌翻译
一个良好的动作效果预测模型,称为环境模型,对于在机器人控制,推荐系统和患者治疗选择等许多领域中实现样本有效的决策政策学习非常重要。我们可以使用这种模型进行无限的试验来确定适当的行动,以便可以节省现实世界中的查询成本。它要求模型正确处理看不见的数据,也称为反事实数据。但是,标准数据拟合技术不会自动实现这种概括能力,通常会导致不可靠的模型。在这项工作中,我们在模型学习中引入了反事实风险最小化(CQRM),以推广到特定目标策略查询的反事实数据集。由于目标策略在政策学习中可能是各种各样且未知的,因此我们提出了一个对抗性CQRM目标,其中模型在对抗性策略查询的反事实数据上学习,并最终得出可拖延的解决方案Galileo。我们还发现,对抗性CQRM与对抗模型学习密切相关,从而解释了后者的有效性。我们将伽利略应用于综合任务和现实应用程序中。结果表明,伽利略对反事实数据做出了准确的预测,从而显着改善了现实世界测试的策略。
translated by 谷歌翻译
Pedestrian detection in the wild remains a challenging problem especially when the scene contains significant occlusion and/or low resolution of the pedestrians to be detected. Existing methods are unable to adapt to these difficult cases while maintaining acceptable performance. In this paper we propose a novel feature learning model, referred to as CircleNet, to achieve feature adaptation by mimicking the process humans looking at low resolution and occluded objects: focusing on it again, at a finer scale, if the object can not be identified clearly for the first time. CircleNet is implemented as a set of feature pyramids and uses weight sharing path augmentation for better feature fusion. It targets at reciprocating feature adaptation and iterative object detection using multiple top-down and bottom-up pathways. To take full advantage of the feature adaptation capability in CircleNet, we design an instance decomposition training strategy to focus on detecting pedestrian instances of various resolutions and different occlusion levels in each cycle. Specifically, CircleNet implements feature ensemble with the idea of hard negative boosting in an end-to-end manner. Experiments on two pedestrian detection datasets, Caltech and CityPersons, show that CircleNet improves the performance of occluded and low-resolution pedestrians with significant margins while maintaining good performance on normal instances.
translated by 谷歌翻译
Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases; and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adopted datasets (ShanghaiTech A\&B, JHU-CROWD++, UCF-QNRF) demonstrate the favorable performance against several state-of-the-art methods.
translated by 谷歌翻译
深度强化学习在基于激光的碰撞避免有效的情况下取得了巨大的成功,因为激光器可以感觉到准确的深度信息而无需太多冗余数据,这可以在算法从模拟环境迁移到现实世界时保持算法的稳健性。但是,高成本激光设备不仅很难为大型机器人部署,而且还表现出对复杂障碍的鲁棒性,包括不规则的障碍,例如桌子,桌子,椅子和架子,以及复杂的地面和特殊材料。在本文中,我们提出了一个新型的基于单眼相机的复杂障碍避免框架。特别是,我们创新地将捕获的RGB图像转换为伪激光测量,以进行有效的深度强化学习。与在一定高度捕获的传统激光测量相比,仅包含距离附近障碍的一维距离信息,我们提议的伪激光测量融合了捕获的RGB图像的深度和语义信息,这使我们的方法有效地有效障碍。我们还设计了一个功能提取引导模块,以加重输入伪激光测量,并且代理对当前状态具有更合理的关注,这有利于提高障碍避免政策的准确性和效率。
translated by 谷歌翻译
边界盒注释表单是可视对象本地化任务最常用的方法。然而,边界盒注释依赖于大量的精确注释的边界盒,这是昂贵的,艰苦的,因此在实际情况下是不可能的,对于某些应用而言,关心尺寸的一些应用甚至是多余的。因此,我们通过将每个人作为粗略点(COARSOPPOINT)向每个人提供注释来提出一种基于点的基于点的框架,该框架可以是对象范围内的任何点,而不是精确的边界框。然后将该人的位置预测为图像中的2D坐标。大大简化了数据注释管道。然而,COARSOUNTPOINT注释不可避免地导致标签可靠性降低(标签不确定性)和训练期间的网络混淆。因此,我们提出了一种点自我细化方法,它以自重节奏的方式迭代地更新点注释。拟议的细化系统减轻了标签不确定性,逐步提高了本地化绩效。实验表明,我们的方法可实现对象本地化性能,同时保存注释成本高达80 $ \%$。代码括在补充材料中。
translated by 谷歌翻译
通过主动学习(AL)获取最具代表性示例,可以通过最大限度地减少图像级或像素 - 明智的注释的努力来使许多数据相关的计算机视觉任务受益。在本文中,我们提出了一种新颖的协作Panoptic-Cable活动学习框架(CPRAL)来解决语义细分任务。对于最初用像素 - WISE注释采样的一小批图像,我们采用Panoptic信息来最初选择未标记的样本。考虑到分段数据集中的类别不平衡,我们导入区域高斯注意模块(RGA)以实现语义偏置选择。该子集通过投票熵突出显示,然后由高斯内核参加,以最大化偏置区域。我们还提出了一个上下文标签扩展(CLE),以提高区域注释,具有语境关注指导。通过协作语义 - 不可知的Panoptic匹配和区域缺陷的选择和延伸,我们的CPRAL可以在标签努力和性能之间取得平衡,并妥协语义分布。我们对城市景观和BDD10K数据集进行了广泛的实验,并表明CPRAL以令人印象深刻的结果和较少的标记比例优于尖端方法。
translated by 谷歌翻译
Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple different domains, and may not contain labels for training. Certain settings, for instance medical applications, often involve further restrictions that prohibit retention of previously seen data due to privacy regulations. In this work, to address such challenges, we study unsupervised segmentation in continual learning scenarios that involve domain shift. To that end, we introduce GarDA (Generative Appearance Replay for continual Domain Adaptation), a generative-replay based approach that can adapt a segmentation model sequentially to new domains with unlabeled data. In contrast to single-step unsupervised domain adaptation (UDA), continual adaptation to a sequence of domains enables leveraging and consolidation of information from multiple domains. Unlike previous approaches in incremental UDA, our method does not require access to previously seen data, making it applicable in many practical scenarios. We evaluate GarDA on two datasets with different organs and modalities, where it substantially outperforms existing techniques.
translated by 谷歌翻译