样本分配在现代对象检测方法中起着重要的作用。但是,大多数现有的方法都依靠手动设计来分配正 /负样本,这些样本并未明确建立样本分配和对象检测性能之间的关系。在这项工作中,我们提出了一种基于高参数搜索的新型动态样本分配方案。我们首先将分配给每个地面真理的正样本的数量定义为超参数,并采用替代优化算法来得出最佳选择。然后,我们设计一个动态的样本分配过程,以动态选择每个训练迭代中的最佳阳性数量。实验表明,所得的HPS-DET在不同对象检测基线的基线上带来了改善的性能。此外,我们分析了在不同数据集之间和不同骨架之间转移的高参数可重复使用性,以进行对象检测,这表现出我们方法的优势和多功能性。
translated by 谷歌翻译
Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve stateof-the-art detectors by a large margin to 50.7% AP without introducing any overhead. The code is available at https://github.com/sfzhang15/ATSS.
translated by 谷歌翻译
我们提出对象盒,这是一种新颖的单阶段锚定且高度可推广的对象检测方法。与现有的基于锚固的探测器和无锚的探测器相反,它们更偏向于其标签分配中的特定对象量表,我们仅将对象中心位置用作正样本,并在不同的特征级别中平均处理所有对象,而不论对象'尺寸或形状。具体而言,我们的标签分配策略将对象中心位置视为形状和尺寸不足的锚定,并以无锚固的方式锚定,并允许学习每个对象的所有尺度。为了支持这一点,我们将新的回归目标定义为从中心单元位置的两个角到边界框的四个侧面的距离。此外,为了处理比例变化的对象,我们提出了一个量身定制的损失来处理不同尺寸的盒子。结果,我们提出的对象检测器不需要在数据集中调整任何依赖数据集的超参数。我们在MS-Coco 2017和Pascal VOC 2012数据集上评估了我们的方法,并将我们的结果与最先进的方法进行比较。我们观察到,与先前的作品相比,对象盒的性能优惠。此外,我们执行严格的消融实验来评估我们方法的不同组成部分。我们的代码可在以下网址提供:https://github.com/mohsenzand/objectbox。
translated by 谷歌翻译
物体检测在计算机视觉中取得了巨大的进步。具有外观降级的小物体检测是一个突出的挑战,特别是对于鸟瞰观察。为了收集足够的阳性/阴性样本进行启发式训练,大多数物体探测器预设区域锚,以便将交叉联盟(iou)计算在地面判处符号数据上。在这种情况下,小物体经常被遗弃或误标定。在本文中,我们提出了一种有效的动态增强锚(DEA)网络,用于构建新颖的训练样本发生器。与其他最先进的技术不同,所提出的网络利用样品鉴别器来实现基于锚的单元和无锚单元之间的交互式样本筛选,以产生符合资格的样本。此外,通过基于保守的基于锚的推理方案的多任务联合训练增强了所提出的模型的性能,同时降低计算复杂性。所提出的方案支持定向和水平对象检测任务。对两个具有挑战性的空中基准(即,DotA和HRSC2016)的广泛实验表明,我们的方法以适度推理速度和用于训练的计算开销的准确性实现最先进的性能。在DotA上,我们的DEA-NET与ROI变压器的基线集成了0.40%平均平均精度(MAP)的先进方法,以便用较弱的骨干网(Resnet-101 VS Resnet-152)和3.08%平均 - 平均精度(MAP),具有相同骨干网的水平对象检测。此外,我们的DEA网与重新排列的基线一体化实现最先进的性能80.37%。在HRSC2016上,它仅使用3个水平锚点超过1.1%的最佳型号。
translated by 谷歌翻译
无锚的检测器基本上将对象检测作为密集的分类和回归。对于流行的无锚检测器,通常是引入单个预测分支来估计本地化的质量。当我们深入研究分类和质量估计的实践时,会观察到以下不一致之处。首先,对于某些分配了完全不同标签的相邻样品,训练有素的模型将产生相似的分类分数。这违反了训练目标并导致绩效退化。其次,发现检测到具有较高信心的边界框与相应的地面真相具有较小的重叠。准确的局部边界框将被非最大抑制(NMS)过程中的精确量抑制。为了解决不一致问题,提出了动态平滑标签分配(DSLA)方法。基于最初在FCO中开发的中心概念,提出了平稳的分配策略。在[0,1]中将标签平滑至连续值,以在正样品和负样品之间稳定过渡。联合(IOU)在训练过程中会动态预测,并与平滑标签结合。分配动态平滑标签以监督分类分支。在这样的监督下,质量估计分支自然合并为分类分支,这简化了无锚探测器的体系结构。全面的实验是在MS Coco基准上进行的。已经证明,DSLA可以通过减轻上述无锚固探测器的不一致来显着提高检测准确性。我们的代码在https://github.com/yonghaohe/dsla上发布。
translated by 谷歌翻译
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at:tinyurl.com/FCOSv1
translated by 谷歌翻译
标签分配在现代对象检测模型中起着重要作用。检测模型可能会通过不同的标签分配策略产生完全不同的性能。对于基于锚的检测模型,锚点及其相应的地面真实边界框之间的IO(与联合的交点)是关键要素,因为正面样品和负样品除以IOU阈值。早期对象探测器仅利用所有训练样本的固定阈值,而最近的检测算法则基于基于IOUS到地面真相框的分布而着重于自适应阈值。在本文中,我们介绍了一种简单的同时有效的方法,可以根据预测的培训状态动态执行标签分配。通过在标签分配中引入预测,选择了更高的地面真相对象的高质量样本作为正样本,这可以减少分类得分和IOU分数之间的差异,并生成更高质量的边界框。我们的方法显示了使用自适应标签分配算法和这些正面样本的下限框损失的检测模型的性能的改进,这表明将更多具有较高质量预测盒的样品选择为阳性。
translated by 谷歌翻译
特征金字塔网络(FPN)是对象检测器的关键组件之一。但是,对于研究人员来说,长期存在的难题是,引入FPN后通常会抑制大规模物体的检测性能。为此,本文首先在检测框架中重新审视FPN,并从优化的角度揭示了FPN成功的性质。然后,我们指出,大规模对象的性能退化是由于集成FPN后出现不当后传播路径所致。它使每个骨干网络的每个级别都只能查看一定尺度范围内的对象。基于这些分析,提出了两种可行的策略,以使每个级别的级别能够查看基于FPN的检测框架中的所有对象。具体而言,一个是引入辅助目标功能,以使每个骨干级在训练过程中直接接收各种尺度对象的后传播信号。另一个是以更合理的方式构建特征金字塔,以避免非理性的背部传播路径。对可可基准测试的广泛实验验证了我们的分析的健全性和方法的有效性。没有铃铛和口哨,我们证明了我们的方法在各种检测框架上实现了可靠的改进(超过2%):一阶段,两阶段,基于锚的,无锚和变压器的检测器。
translated by 谷歌翻译
对象检测是典型的多任务学习应用程序,其同时优化分类和回归。但是,分类损失总是以基于锚的方法的多任务损失主导,妨碍了任务的一致和平衡优化。在本文中,我们发现转移边界盒可以在分类中改变正面和负样本的划分,意思是分类取决于回归。此外,考虑到不同的数据集,优化器和回归损耗功能,我们总结了关于微调损耗重量的三个重要结论。基于上述结论,我们提出了自适应损失重量调整(ALWA)以根据损失的统计特征来解决优化基于锚的方法的不平衡。通过将Alwa纳入以前的最先进的探测器,我们在Pascal VOC和MS Coco上实现了显着的性能增益,即使是L1,Smoothl1和Ciou丢失。代码可在https://github.com/ywx-hub/alwa获得。
translated by 谷歌翻译
检测微小的物体是一个非常具有挑战性的问题,因为一个小物体只包含几个像素的大小。我们证明,由于缺乏外观信息,最新的检测器不会对微小物体产生令人满意的结果。我们的主要观察结果是,基于联合(IOU)的相交(例如IOU本身及其扩展)对微小物体的位置偏差非常敏感,并且在基于锚固的检测器中使用时会大大恶化检测性能。为了减轻这一点,我们提出了使用Wasserstein距离进行微小对象检测的新评估度量。具体而言,我们首先将边界框建模为2D高斯分布,然后提出一个新的公制称为标准化的瓦斯汀距离(NWD),以通过相应的高斯分布来计算它们之间的相似性。提出的NWD度量可以轻松地嵌入分配中,非最大抑制作用以及任何基于锚固的检测器的损耗函数,以替换常用的IOU度量。我们在新的数据集上评估了我们的度量,以用于微小对象检测(AI-TOD),其中平均对象大小比现有对象检测数据集小得多。广泛的实验表明,在配备NWD指标时,我们的方法的性能比标准的微调基线高6.7 AP点,并且比最先进的竞争对手高6.0 AP点。代码可在以下网址提供:https://github.com/jwwangchn/nwd。
translated by 谷歌翻译
Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present RepPoints (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to automatically arrange themselves in a manner that bounds the spatial extent of an object and indicates semantically significant local areas. They furthermore do not require the use of anchors to sample a space of bounding boxes. We show that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 AP 50 on the COCO test-dev detection benchmark, using ResNet-101 model. Code is available at https://github.com/microsoft/RepPoints.
translated by 谷歌翻译
现有的实例分割方法已经达到了令人印象深刻的表现,但仍遭受了共同的困境:一个实例推断出冗余表示(例如,多个框,网格和锚点),这导致了多个重复的预测。因此,主流方法通常依赖于手工设计的非最大抑制(NMS)后处理步骤来选择最佳预测结果,这会阻碍端到端训练。为了解决此问题,我们建议一个称为Uniinst的无盒和无端机实例分割框架,该框架仅对每个实例产生一个唯一的表示。具体而言,我们设计了一种实例意识到的一对一分配方案,即仅产生一个表示(Oyor),该方案根据预测和地面真相之间的匹配质量,动态地为每个实例动态分配一个独特的表示。然后,一种新颖的预测重新排列策略被优雅地集成到框架中,以解决分类评分和掩盖质量之间的错位,从而使学习的表示形式更具歧视性。借助这些技术,我们的Uniinst,第一个基于FCN的盒子和无NMS实例分段框架,实现竞争性能,例如,使用Resnet-50-FPN和40.2 mask AP使用Resnet-101-FPN,使用Resnet-50-FPN和40.2 mask AP,使用Resnet-101-FPN,对抗AP可可测试-DEV的主流方法。此外,提出的实例感知方法对于遮挡场景是可靠的,在重锁定的ochuman基准上,通过杰出的掩码AP优于公共基线。我们的代码将在出版后提供。
translated by 谷歌翻译
Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different targets, i.e., the object category and boundaries, are generally different. Predicting all these targets from the same grid location thus may lead to sub-optimal results. In this paper, we analyze the suitable inference positions for object category and boundaries, and propose a prediction-target-decoupled detector named PDNet to establish a more flexible detection paradigm. Our PDNet with the prediction decoupling mechanism encodes different targets separately in different locations. A learnable prediction collection module is devised with two sets of dynamic points, i.e., dynamic boundary points and semantic points, to collect and aggregate the predictions from the favorable regions for localization and classification. We adopt a two-step strategy to learn these dynamic point positions, where the prior positions are estimated for different targets first, and the network further predicts residual offsets to the positions with better perceptions of the object properties. Extensive experiments on the MS COCO benchmark demonstrate the effectiveness and efficiency of our method. With a single ResNeXt-64x4d-101-DCN as the backbone, our detector achieves 50.1 AP with single-scale testing, which outperforms the state-of-the-art methods by an appreciable margin under the same experimental settings.Moreover, our detector is highly efficient as a one-stage framework. Our code is public at https://github.com/yangli18/PDNet.
translated by 谷歌翻译
现实世界中的对象检测模型应便宜且准确。知识蒸馏(KD)可以通过利用大型教师模型的有用信息来提高小型,廉价检测模型的准确性。但是,一个关键的挑战是确定老师进行蒸馏产生的最有用的功能。在这项工作中,我们表明,在地面边界框中只有一小部分功能才是老师的高检测性能。基于此,我们提出了预测引导的蒸馏(PGD),该蒸馏将蒸馏放在教师的这些关键预测区域上,并在许多现有的KD基准方面的性能取得了可观的增长。此外,我们建议对关键区域进行自适应加权方案,以平滑其影响力并取得更好的性能。我们提出的方法在各种高级一阶段检测体系中的当前最新KD基准都优于当前的最新KD基线。具体而言,在可可数据集上,我们的方法分别使用RESNET-101和RESNET-50作为教师和学生骨架,在 +3.1%和 +4.6%的AP改进之间达到了AP的改善。在CrowdHuman数据集上,我们还使用这些骨架,在MR和AP上取得了 +3.2%和 +2.0%的提高。我们的代码可在https://github.com/chenhongyiyang/pgd上找到。
translated by 谷歌翻译
航空图像中的微小对象检测(TOD)是具有挑战性的,因为一个小物体只包含几个像素。最先进的对象探测器由于缺乏判别特征的监督而无法为微小对象提供令人满意的结果。我们的主要观察结果是,联合度量(IOU)及其扩展的相交对微小物体的位置偏差非常敏感,这在基于锚固的探测器中使用时会大大恶化标签分配的质量。为了解决这个问题,我们提出了一种新的评估度量标准,称为标准化的Wasserstein距离(NWD)和一个新的基于排名的分配(RKA)策略,以进行微小对象检测。提出的NWD-RKA策略可以轻松地嵌入到各种基于锚的探测器中,以取代标准的基于阈值的检测器,从而大大改善了标签分配并为网络培训提供了足够的监督信息。在四个数据集中测试,NWD-RKA可以始终如一地提高微小的对象检测性能。此外,在空中图像(AI-TOD)数据集中观察到显着的嘈杂标签,我们有动力将其重新标记并释放AI-TOD-V2及其相应的基准。在AI-TOD-V2中,丢失的注释和位置错误问题得到了大大减轻,从而促进了更可靠的培训和验证过程。将NWD-RKA嵌入探测器中,检测性能比AI-TOD-V2上的最先进竞争对手提高了4.3个AP点。数据集,代码和更多可视化可在以下网址提供:https://chasel-tsui.g​​ithub.io/ai/ai-tod-v2/
translated by 谷歌翻译
translated by 谷歌翻译
In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its quality. While the commonly used threshold of 0.5 leads to noisy (low-quality) detections, detection performance frequently degrades for larger thresholds. This paradox of high-quality detection has two causes: 1) overfitting, due to vanishing positive samples for large thresholds, and 2) inference-time quality mismatch between detector and test hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, composed of a sequence of detectors trained with increasing IoU thresholds, is proposed to address these problems. The detectors are trained sequentially, using the output of a detector as training set for the next. This resampling progressively improves hypotheses quality, guaranteeing a positive training set of equivalent size for all detectors and minimizing overfitting. The same cascade is applied at inference, to eliminate quality mismatches between hypotheses and detectors. An implementation of the Cascade R-CNN without bells or whistles achieves state-of-the-art performance on the COCO dataset, and significantly improves high-quality detection on generic and specific object detection datasets, including VOC, KITTI, CityPerson, and WiderFace. Finally, the Cascade R-CNN is generalized to instance segmentation, with nontrivial improvements over the Mask R-CNN. To facilitate future research, two implementations are made available at https://github.com/zhaoweicai/cascade-rcnn (Caffe) and https://github.com/zhaoweicai/Detectron-Cascade-RCNN (Detectron).
translated by 谷歌翻译
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This makes properly localized bounding boxes degenerate during iterative regression or even suppressed during NMS. In the paper we propose IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth. The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes. Furthermore, an optimization-based bounding box refinement method is proposed, where the predicted IoU is formulated as the objective. Extensive experiments on the MS-COCO dataset show the effectiveness of IoU-Net, as well as its compatibility with and adaptivity to several state-of-the-art object detectors.
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