Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels -sample level, feature level, and objective level. To mitigate the adverse effects caused thereby, we propose Libra R-CNN, a simple but effective framework towards balanced learning for object detection. It integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level. Benefitted from the overall balanced design, Libra R-CNN significantly improves the detection performance. Without bells and whistles, it achieves 2.5 points and 2.0 points higher Average Precision (AP) than FPN Faster R-CNN and RetinaNet respectively on MSCOCO. 1

Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4% and 1.5% improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at: https://github.com/ open-mmlab/mmdetection.

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.

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).

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。

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。

复杂的水下环境为物体检测带来了新的挑战，例如未平衡的光条件，低对比度，阻塞和水生生物的模仿。在这种情况下，水下相机捕获的物体将变得模糊，并且通用探测器通常会在这些模糊的物体上失败。这项工作旨在从两个角度解决问题：不确定性建模和艰难的例子采矿。我们提出了一个名为Boosting R-CNN的两阶段水下检测器，该检测器包括三个关键组件。首先，提出了一个名为RetinArpn的新区域建议网络，该网络提供了高质量的建议，并考虑了对象和IOU预测，以确定对象事先概率的不确定性。其次，引入了概率推理管道，以结合第一阶段的先验不确定性和第二阶段分类评分，以模拟最终检测分数。最后，我们提出了一种名为Boosting Reweighting的新的硬示例挖掘方法。具体而言，当区域提案网络误认为样品的对象的事先概率时，提高重新加权将在训练过程中增加R-CNN头部样品的分类损失，同时减少具有准确估计的先验的简易样品丢失。因此，可以在第二阶段获得强大的检测头。在推理阶段，R-CNN具有纠正第一阶段的误差以提高性能的能力。在两个水下数据集和两个通用对象检测数据集上进行的全面实验证明了我们方法的有效性和鲁棒性。

由于卷积在提取物体的局部上下文中，在过去十年中，对象检测在过去十年中取得了重大进展。但是，对象的尺度是多样的，当前卷积只能处理单尺度输入。因此，传统卷积具有固定接收场在处理这种规模差异问题方面的能力受到限制。多尺度功能表示已被证明是缓解规模差异问题的有效方法。最近的研究主要与某些量表或各个尺度的总体特征采用部分联系，并专注于整个量表的全球信息。但是，跨空间和深度维度的信息被忽略了。受此启发，我们提出了多尺度卷积（MSCONV）来解决此问题。同时考虑到量表，空间和深度信息，MSCONV能够更全面地处理多尺度输入。 MSCONV是有效的，并且在计算上是有效的，只有少量计算成本增加。对于大多数单阶段对象探测器，在检测头中用MSCONV代替传统的卷积可以带来AP的2.5 \％改进（在Coco 2017数据集上），只有3 \％的拖鞋增加了。 MSCONV对于两阶段对象探测器也具有灵活性和有效性。当扩展到主流两阶段对象检测器时，MSCONV的AP可以提高3.0 \％。我们在单尺度测试下的最佳模型在Coco 2017上实现了48.9 \％AP，\ textit {test-dev} Split，它超过了许多最新方法。

在对象检测中，边界框回归（BBR）是决定对象定位性能的关键步骤。但是，我们发现BBR的大多数先前的损失功能都有两个主要缺点：（i）$ \ ell_n $ -norm和IOU基于IOU的损失功能都无法效率地描述BBR的目标，这会导致收敛速度缓慢和不准确的回归结果。 。 （ii）大多数损失函数都忽略了BBR中的不平衡问题，即与目标盒有较小重叠的大量锚盒对BBR的优化有最大的影响。为了减轻造成的不利影响，我们进行了彻底的研究，以利用本文中BBR损失的潜力。首先，提出了有关联合（EIOU）损失的有效交集，该交集明确测量了BBR中三个几何因素的差异，即重叠面积，中心点和侧面长度。之后，我们说明有效的示例挖掘（EEM）问题，并提出了焦点损失的回归版本，以使回归过程集中在高质量的锚点上。最后，将上述两个部分组合在一起以获得新的损失函数，即焦点损失。对合成数据集和真实数据集进行了广泛的实验。与其他BBR损失相比，在收敛速度和定位精度上都可以显着优势。

锥体网络是多尺度对象检测的标准方法。当前对特征金字塔网络的研究通常采用层连接来从特征层次结构的某些级别收集特征，并且不考虑它们之间的显着差异。我们提出了一个更好的特征金字塔网络的体系结构，称为选择性多尺度学习（SMSL），以解决此问题。SMSL高效且泛滥，可以将其集成到单阶段和两阶段检测器中以提高检测性能，几乎没有额外的推理成本。视网膜与SMSL的结合获得了可可数据集的AP（从39.1 \％到40.9 \％）的1.8 \％改进。与SMSL集成时，两阶段探测器的AP可以提高1.0 \％。

尽管近期长尾对象检测成功，但几乎所有长尾对象探测器都是基于两级范式开发的。在实践中，一阶段探测器在行业中更为普遍，因为它们具有简单而快速的管道，易于部署。然而，在长尾情景中，到目前为止，这项工作尚未探讨。在本文中，我们调查了在这种情况下是否可以良好的单级探测器表现良好。我们发现预防一步检测器实现优异性能的主要障碍是：在长尾数据分布下，类别遭受不同程度的正负不平衡问题。传统的焦点损失与所有类别的调制因子相同的调节因子平衡，因此未能处理长尾问题。为了解决这个问题，我们提出了根据其不平衡程度独立地重新平衡不同类别的正面和负样本的损失贡献的均等的联络损失（EFL）。具体而言，EFL采用类别相关调制因子，可以通过不同类别的培训状态来动态调整。对挑战性的LVIS V1基准进行的广泛实验表明了我们提出的方法的有效性。通过端到端培训管道，EF​​L在整体AP方面实现了29.2％，并对稀有类别进行了显着的性能改进，超越了所有现有的最先进的方法。代码可在https://github.com/modeltc/eod上获得。

The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framework. Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature. We present adaptive feature pooling, which links feature grid and all feature levels to make useful information in each feature level propagate directly to following proposal subnetworks. A complementary branch capturing different views for each proposal is created to further improve mask prediction.These improvements are simple to implement, with subtle extra computational overhead. Our PANet reaches the 1 st place in the COCO 2017 Challenge Instance Segmentation task and the 2 nd place in Object Detection task without large-batch training. It is also state-of-the-art on MVD and Cityscapes. Code is available at https://github. com/ShuLiu1993/PANet.

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A topdown architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using FPN in a basic Faster R-CNN system, our method achieves state-of-the-art singlemodel results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 6 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.

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。

Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance segmentation frameworks. However, the mask quality, quantified as the IoU between the instance mask and its ground truth, is usually not well correlated with classification score. In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks. The proposed network block takes the instance feature and the corresponding predicted mask together to regress the mask IoU. The mask scoring strategy calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. By extensive evaluations on the COCO dataset, Mask Scoring R-CNN brings consistent and noticeable gain with different models, and outperforms the state-of-the-art Mask R-CNN. We hope our simple and effective approach will provide a new direction for improving instance segmentation. The source code of our method is available at https:// github.com/zjhuang22/maskscoring_rcnn. * The work was done when Zhaojin Huang was an intern in Horizon Robotics Inc.

平均精度（AP）损失最近在密集的对象检测任务上显示出有希望的性能。但是，尚未开发出对AP损失如何影响检测器的深刻了解。在这项工作中，我们重新审视平均精度（AP）损失，并揭示了关键元素是选择排名对的关键元素基于该观察结果，我们提出了两种改善AP损失的策略。其中的第一个是一种新型的自适应成对误差（APE）损失，该损失集中在正面和负样本中的排名对。此外，我们通过使用聚类算法利用归一化排名得分和本地化得分来选择更准确的排名对。在MSCOCO数据集上进行的实验支持我们的分析，并证明了我们提出的方法的优越性与当前分类和排名损失相比。该代码可从https://github.com/xudangliatiger/ape-loss获得。

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。

特征金字塔网络（FPN）已成为对象检测模型考虑对象的各种尺度的重要模块。但是，小物体上的平均精度（AP）相对低于中和大物体上的AP。原因是CNN较深层导致信息丢失作为特征提取水平的原因。我们提出了一个新的比例顺序（S^2）特征FPN的特征提取，以增强小物体的特征信息。我们将FPN结构视为尺度空间和提取尺度序列（s^2）特征，该特征是在FPN的水平轴上通过3D卷积。它基本上是扩展不变的功能，并建立在小物体的高分辨率金字塔功能图上。此外，建议的S^2功能可以扩展到基于FPN的大多数对象检测模型。我们证明所提出的S2功能可以提高COCO数据集中一阶段和两阶段探测器的性能。根据提出的S2功能，我们分别为Yolov4-P5和Yolov4-P6获得了高达1.3％和1.1％的AP改善。对于更快的RCNN和Mask R-CNN，我们分别观察到AP改进的2.0％和1.6％，分别具有建议的S^2功能。

在传统的对象检测框架中，从图像识别模型继承的骨干体提取了深层特征，然后颈部模块融合了这些潜在特征，以在不同的尺度上捕获信息。由于对象检测的分辨率比图像识别大得多，因此骨干的计算成本通常主导了总推断成本。这种沉重的背部设计范式主要是由于历史遗产将图像识别模型传输到对象检测时，而不是端到端的优化设计以进行对象检测。在这项工作中，我们表明这种范式确实导致了亚最佳对象检测模型。为此，我们提出了一种新型的重颈范式，长颈鹿，这是一个类似长颈鹿的网络，用于有效的对象检测。长颈鹿使用极轻的骨干和非常深的颈部模块，可同时同时在不同的空间尺度以及不同级别的潜在语义之间进行密集的信息交换。该设计范式允许检测器即使在网络的早期阶段，也可以在相同的优先级处理高级语义信息和低级空间信息，从而使其在检测任务中更有效。对多个流行对象检测基准的数值评估表明，长颈鹿在广泛的资源约束中始终优于先前的SOTA模型。源代码可在https://github.com/jyqi/giraffedet上获得。