最近在对象检测和细分领域取得了重大进步。但是，当涉及到罕见类别时，最新方法无法检测到它们，从而在稀有类别和频繁类别之间存在显着的性能差距。在本文中，我们确定深探测器中使用的Sigmoid或SoftMax函数是低性能的主要原因，并且是长尾检测和分割的最佳选择。为了解决这个问题，我们开发了牙龈优化的损失（GOL），以进行长尾检测和分割。考虑到大多数长尾检测中的大多数类的预期概率较低，它与数据集中罕见类别的牙胶分布保持一致。拟议的GOL在AP上显着优于最佳最新方法的最佳方法，并将整体分割率提高9.0％，并将检测到8.0％，尤其是将稀有类别的检测提高了20.3％，与Mask-Rcnn相比提高了20.3％。 ，在LVIS数据集上。代码可用：https：//github.com/kostas1515/gol

长尾分布是现实世界中的常见现象。提取的大规模图像数据集不可避免地证明了长尾巴的属性和经过不平衡数据训练的模型可以为代表性过多的类别获得高性能，但为代表性不足的类别而苦苦挣扎，导致偏见的预测和绩效降低。为了应对这一挑战，我们提出了一种名为“逆图像频率”（IIF）的新型偏差方法。 IIF是卷积神经网络分类层中逻辑的乘法边缘调整转换。我们的方法比类似的作品实现了更强的性能，并且对于下游任务（例如长尾实例分割）特别有用，因为它会产生较少的假阳性检测。我们的广泛实验表明，IIF在许多长尾基准的基准（例如Imagenet-lt，cifar-lt，ploce-lt和lvis）上超过了最先进的现状，在Imagenet-lt上，Resnet50和26.2％达到了55.8％的TOP-1准确性LVIS上使用MaskRCNN分割AP。代码可在https://github.com/kostas1515/iif中找到

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS.In this work, we analyze this problem from a novel perspective: each positive sample of one category can be seen as a negative sample for other categories, making the tail categories receive more discouraging gradients. Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories. The equalization loss protects the learning of rare categories from being at a disadvantage during the network parameter updating. Thus the model is capable of learning better discriminative features for objects of rare classes. Without any bells and whistles, our method achieves AP gains of 4.1% and 4.8% for the rare and common categories on the challenging LVIS benchmark, compared to the Mask R-CNN baseline. With the utilization of the effective equalization loss, we finally won the 1st place in the LVIS Challenge 2019. Code has been made available at: https: //github.com/tztztztztz/eql.detectron2

Vanilla用于物体检测和实例分割的模型遭受重偏向朝着长尾设置中的频繁对象进行偏向。现有方法主要在培训期间解决此问题，例如，通过重新采样或重新加权。在本文中，我们调查了一个很大程度上被忽视的方法 - 置信分数的后处理校准。我们提出NORCAL，用于长尾对象检测和实例分割的归一化校准校准，简单而简单的配方，通过其训练样本大小重新恢复每个阶级的预测得分。我们展示了单独处理背景类并使每个提案的课程分数标准化是实现卓越性能的键。在LVIS DataSet上，Norcal不仅可以在罕见的课程上有效地改善所有基线模型，也可以在普通和频繁的阶级上改进。最后，我们进行了广泛的分析和消融研究，以了解我们方法的各种建模选择和机制的见解。我们的代码在https://github.com/tydpan/norcal/上公开提供。

由于课程中的训练样本极端不平衡，长尾实例分割是一个具有挑战性的任务。它导致头部课程的严重偏差（含有多数样本）对尾尾。这呈现“如何适当地定义和缓解偏见”最重要的问题之一。先前作品主要使用标签分布或平均分数信息来表示粗粒偏置。在本文中，我们探索挖掘困难的矩阵，该矩阵携带细粒度的错误分类细节，以减轻成对偏置，概括粗液。为此，我们提出了一种新颖的成对类余额（PCB）方法，基于混淆矩阵，在训练期间更新以累积正在进行的预测偏好。 PCB在培训期间生成正规化的纠错软标签。此外，开发了一种迭代学习范例，以支持这种脱结的渐进和平稳的正则化。 PCB可以插入并播放任何现有方法作为补充。 LVIS的实验结果表明，我们的方法在没有钟声和口哨的情况下实现最先进的性能。各种架构的卓越结果表明了泛化能力。

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。

As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are long-tailed in nature; it is even impossible when the sample-of-interest co-exists with each other in one collectable unit, e.g., multiple visual instances in one image. Therefore, long-tailed classification is the key to deep learning at scale. However, existing methods are mainly based on reweighting/re-sampling heuristics that lack a fundamental theory. In this paper, we establish a causal inference framework, which not only unravels the whys of previous methods, but also derives a new principled solution. Specifically, our theory shows that the SGD momentum is essentially a confounder in long-tailed classification. On one hand, it has a harmful causal effect that misleads the tail prediction biased towards the head. On the other hand, its induced mediation also benefits the representation learning and head prediction. Our framework elegantly disentangles the paradoxical effects of the momentum, by pursuing the direct causal effect caused by an input sample. In particular, we use causal intervention in training, and counterfactual reasoning in inference, to remove the "bad" while keep the "good". We achieve new state-of-the-arts on three long-tailed visual recognition benchmarks 1 : Long-tailed CIFAR-10/-100, ImageNet-LT for image classification and LVIS for instance segmentation.

由于癌症样品收集和注释的难度，宫颈癌数据集通常表现出长尾数据分布。当训练检测器以检测WSI（整个切片图像）中的癌细胞时，从TCT（ThinPrep细胞学测试）样品捕获的样品时，头部类别（例如正常细胞和炎性细胞）通常比尾巴类别数量更大。 （例如癌细胞）。对象检测中的大多数现有最新的长尾学习方法将重点放在类别分布统计上，以解决长尾方案中的问题，而无需考虑每个样本的“硬度”。为了解决这个问题，在这项工作中，我们提出了一个Grad-libra损失，该损失利用梯度动态校准每个样品的硬度程度，以使不同类别的硬度度重新平衡正面和负样品的梯度。因此，我们的损失可以帮助探测器更加重视头部和尾部类别中的这些硬样品。在长尾的TCT WSI图像数据集上进行了广泛的实验表明，主流检测器，例如对使用我们建议的梯度损失训练的训练，重新点，FCO，ATSS，YOLOF等的地图比使用跨透明分类损失训练的地图要高得多（7.8％）。

与其他类别（称为少数族裔或尾巴类）相比，很少的类或类别（称为多数或头等类别的类别）具有更高的数据样本数量，在现实世界中，长尾数据集经常遇到。在此类数据集上培训深层神经网络会给质量级别带来偏见。到目前为止，研究人员提出了多种加权损失和数据重新采样技术，以减少偏见。但是，大多数此类技术都认为，尾巴类始终是最难学习的类，因此需要更多的重量或注意力。在这里，我们认为该假设可能并不总是成立的。因此，我们提出了一种新颖的方法，可以在模型的训练阶段动态测量每个类别的瞬时难度。此外，我们使用每个班级的难度度量来设计一种新型的加权损失技术，称为“基于阶级难度的加权（CDB-W）损失”和一种新型的数据采样技术，称为“基于类别难度的采样）（CDB-S ）'。为了验证CDB方法的广泛可用性，我们对多个任务进行了广泛的实验，例如图像分类，对象检测，实例分割和视频操作分类。结果验证了CDB-W损失和CDB-S可以在许多类似于现实世界中用例的类别不平衡数据集（例如Imagenet-LT，LVIS和EGTEA）上实现最先进的结果。

长尾学习旨在应对在现实情况下严重的阶级失衡下统治训练程序的关键挑战。但是，很少有人注意如何量化表示空间中头等的优势严重性。在此激励的情况下，我们将基于余弦的分类器推广到von mises-fisher（VMF）混合模型，该模型被称为VMF分类器，该模型可以通过计算分布重叠系数来定量地测量超晶体空间上的表示质量。据我们所知，这是从分布重叠系数的角度来衡量分类器和特征的表示质量的第一项工作。最重要的是，我们制定了类间差异和类功能的一致性损失项，以减轻分类器的重量之间的干扰，并与分类器的权重相结合。此外，一种新型的训练后校准算法设计为零成本通过类间重叠系数来提高性能。我们的方法的表现优于先前的工作，并具有很大的利润，并在长尾图像分类，语义细分和实例分段任务上实现了最先进的性能（例如，我们在Imagenet-50中实现了55.0 \％的总体准确性LT）。我们的代码可在https://github.com/vipailab/vmf \_op上找到。

Building instance segmentation models that are dataefficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge. Here, we perform a systematic study of the Copy-Paste augmentation (e.g., [13,12]) for instance segmentation where we randomly paste objects onto an image. Prior studies on Copy-Paste relied on modeling the surrounding visual context for pasting the objects. However, we find that the simple mechanism of pasting objects randomly is good enough and can provide solid gains on top of strong baselines. Furthermore, we show Copy-Paste is additive with semi-supervised methods that leverage extra data through pseudo labeling (e.g. self-training). On COCO instance segmentation, we achieve 49.1 mask AP and 57.3 box AP, an improvement of +0.6 mask AP and +1.5 box AP over the previous state-of-the-art. We further demonstrate that Copy-Paste can lead to significant improvements on the LVIS benchmark. Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3.6 mask AP on rare categories.

我们提出了一种称为分配 - 均衡损失的新损失功能，用于展示长尾类分布的多标签识别问题。与传统的单标分类问题相比，由于两个重要问题，多标签识别问题通常更具挑战性，即标签的共同发生以及负标签的主导地位（当被视为多个二进制分类问题时）。分配 - 平衡损失通过对标准二进制交叉熵丢失的两个关键修改来解决这些问题：1）重新平衡考虑标签共发生造成的影响的重量的新方法，以及2）负耐受规则化以减轻负标签的过度抑制。 Pascal VOC和Coco的实验表明，使用这种新损失功能训练的模型可实现现有方法的显着性能。代码和型号可在：https://github.com/wutong16/distributionbalancedloss。

视觉识别任务中的长尾类分布对于如何处理头部和尾部类之间的偏置预测，即，模型倾向于将尾部类作为头部类进行分类。虽然现有的研究专注于数据重采采样和损失函数工程，但在本文中，我们采取了不同的视角：分类利润率。我们研究边距和注册之间的关系（分类得分）并经验遵守偏置边缘，并且偏置的Logits是正相关的。我们提出MARC，一个简单但有效的边缘校准函数，用于动态校准偏置边缘的偏置利润。我们通过对普通的长尾基准测试进行了广泛的实验，包括CIFAR-LT，Imagenet-LT，LT，以及不适物 - LT的广泛实验。实验结果表明，我们的MARC在这些基准上实现了有利的结果。此外，Marc只需三行代码即可实现。我们希望这种简单的方法能够激励人们重新思考偏置的边距和偏见的长尾视觉识别标识。

大多数现有的最新视频分类方法假设训练数据遵守统一的分布。但是，现实世界中的视频数据通常会表现出不平衡的长尾巴分布，从而导致模型偏见对头等阶层，并且在尾巴上的性能相对较低。虽然当前的长尾分类方法通常集中在图像分类上，但将其调整到视频数据并不是微不足道的扩展。我们提出了一种端到端的多专家分布校准方法，以基于两级分布信息来应对这些挑战。该方法共同考虑了每个类别中样品的分布（类内部分布）和各种数据（类间分布）的总体分布，以解决在长尾分布下数据不平衡数据的问题。通过对两级分布信息进行建模，该模型可以共同考虑头等阶层和尾部类别，并将知识从头等阶层显着转移，以提高尾部类别的性能。广泛的实验验证了我们的方法是否在长尾视频分类任务上实现了最先进的性能。

The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task. Existing LTR methods seldom train Vision Transformers (ViTs) with Long-Tailed (LT) data, while the off-the-shelf pretrain weight of ViTs always leads to unfair comparisons. In this paper, we systematically investigate the ViTs' performance in LTR and propose LiVT to train ViTs from scratch only with LT data. With the observation that ViTs suffer more severe LTR problems, we conduct Masked Generative Pretraining (MGP) to learn generalized features. With ample and solid evidence, we show that MGP is more robust than supervised manners. In addition, Binary Cross Entropy (BCE) loss, which shows conspicuous performance with ViTs, encounters predicaments in LTR. We further propose the balanced BCE to ameliorate it with strong theoretical groundings. Specially, we derive the unbiased extension of Sigmoid and compensate extra logit margins to deploy it. Our Bal-BCE contributes to the quick convergence of ViTs in just a few epochs. Extensive experiments demonstrate that with MGP and Bal-BCE, LiVT successfully trains ViTs well without any additional data and outperforms comparable state-of-the-art methods significantly, e.g., our ViT-B achieves 81.0% Top-1 accuracy in iNaturalist 2018 without bells and whistles. Code is available at https://github.com/XuZhengzhuo/LiVT.

The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balancing strategies, e.g. by loss re-weighting, data re-sampling, or transfer learning from head-to tail-classes, but most of them adhere to the scheme of jointly learning representations and classifiers. In this work, we decouple the learning procedure into representation learning and classification, and systematically explore how different balancing strategies affect them for long-tailed recognition. The findings are surprising: (1) data imbalance might not be an issue in learning high-quality representations; (2) with representations learned with the simplest instance-balanced (natural) sampling, it is also possible to achieve strong long-tailed recognition ability by adjusting only the classifier. We conduct extensive experiments and set new state-of-the-art performance on common long-tailed benchmarks like ImageNet-LT, Places-LT and iNaturalist, showing that it is possible to outperform carefully designed losses, sampling strategies, even complex modules with memory, by using a straightforward approach that decouples representation and classification. Our code is available at https://github.com/facebookresearch/classifier-balancing.

长尾数据集的泛化差距主要是由于大多数类别仅占占用几个训练样本。解耦培训通过分别培训骨干和分类器来实现更好的性能。导致端到端模型培训的较差的性能（例如，基于Logits利润率的方法）？在这项工作中，我们确定影响分类器的学习的关键因素：在输入分类器之前，具有低熵的通道相关功能。从信息理论的角度来看，我们分析了为什么交叉熵损失倾向于在不平衡数据上产生高度相关的特征。此外，我们理论上的分析和证明对分类器权重的梯度，Hessian的条件数量的影响，以及基于利润率的方法的影响。因此，我们首先建议使用频道美白与去相关（“散点”）分类器的输入用于解耦的权重更新和重塑偏移决策边界，这使得令人满意的结果与基于Logits裕度的方法相结合。但是，当小类课程的数量大，批量不平衡和更多的参与训练导致主要类的过度拟合。我们还提出了两种新颖的模块，基于块的相对平衡的批量采样器（B3RS）和批量嵌入式培训（BET）来解决上述问题，这使得端到端的训练能够实现比解耦训练更好的性能。在长尾分类基准测试，CIFAR-LT和Imagenet-LT上的实验结果证明了我们方法的有效性。

长尾数据集（Head Class）组成的培训样本比尾巴类别多得多，这会导致识别模型对头等舱有偏见。加权损失是缓解此问题的最受欢迎的方法之一，最近的一项工作表明，班级难度可能比常规使用的类频率更好地决定了权重的分布。在先前的工作中使用了一种启发式公式来量化难度，但是我们从经验上发现，最佳公式取决于数据集的特征。因此，我们提出了困难网络，该难题学习在元学习框架中使用模型的性能来预测类的难度。为了使其在其他班级的背景下学习班级的合理难度，我们新介绍了两个关键概念，即相对难度和驾驶员损失。前者有助于困难网络在计算班级难度时考虑其他课程，而后者对于将学习指向有意义的方向是必不可少的。对流行的长尾数据集进行了广泛的实验证明了该方法的有效性，并且在多个长尾数据集上实现了最先进的性能。

In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as predicting contour of instance through instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on the challenging COCO dataset.For the first time, we show that the complexity of instance segmentation, in terms of both design and computation complexity, can be the same as bounding box object detection and this much simpler and flexible instance segmentation framework can achieve competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation task. Code is available at: github.com/xieenze/PolarMask.

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).