Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems -BN's error increases rapidly when the batch size becomes smaller, caused by inaccurate batch statistics estimation. This limits BN's usage for training larger models and transferring features to computer vision tasks including detection, segmentation, and video, which require small batches constrained by memory consumption. In this paper, we present Group Normalization (GN) as a simple alternative to BN. GN divides the channels into groups and computes within each group the mean and variance for normalization. GN's computation is independent of batch sizes, and its accuracy is stable in a wide range of batch sizes. On ResNet-50 trained in ImageNet, GN has 10.6% lower error than its BN counterpart when using a batch size of 2; when using typical batch sizes, GN is comparably good with BN and outperforms other normalization variants. Moreover, GN can be naturally transferred from pre-training to fine-tuning. GN can outperform its BNbased counterparts for object detection and segmentation in COCO, 1 and for video classification in Kinetics, showing that GN can effectively replace the powerful BN in a variety of tasks. GN can be easily implemented by a few lines of code in modern libraries.

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization. The results are no worse than their ImageNet pre-training counterparts even when using the hyper-parameters of the baseline system (Mask R-CNN) that were optimized for fine-tuning pretrained models, with the sole exception of increasing the number of training iterations so the randomly initialized models may converge. Training from random initialization is surprisingly robust; our results hold even when: (i) using only 10% of the training data, (ii) for deeper and wider models, and (iii) for multiple tasks and metrics. Experiments show that ImageNet pre-training speeds up convergence early in training, but does not necessarily provide regularization or improve final target task accuracy. To push the envelope we demonstrate 50.9 AP on COCO object detection without using any external data-a result on par with the top COCO 2017 competition results that used ImageNet pre-training. These observations challenge the conventional wisdom of ImageNet pre-training for dependent tasks and we expect these discoveries will encourage people to rethink the current de facto paradigm of 'pretraining and fine-tuning' in computer vision.

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call "cardinality" (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online 1 .

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method [4] in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our nonlocal models can compete or outperform current competition winners on both Kinetics and Charades datasets.In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code will be made available.

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning [29] as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.

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.

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art accuracy on major video recognition benchmarks, Kinetics, Charades and AVA. Code has been made available at: https://github.com/ facebookresearch/SlowFast.

在本文中，我们将多尺度视觉变压器（MVIT）作为图像和视频分类的统一架构，以及对象检测。我们提出了一种改进的MVIT版本，它包含分解的相对位置嵌入和残余汇集连接。我们以五种尺寸实例化此架构，并评估Imagenet分类，COCO检测和动力学视频识别，在此优先效果。我们进一步比较了MVITS的汇集注意力来窗口注意力机制，其中它在准确性/计算中优于后者。如果没有钟声，MVIT在3个域中具有最先进的性能：ImageNet分类的准确性为88.8％，Coco对象检测的56.1盒AP和动力学-400视频分类的86.1％。代码和模型将公开可用。

Adder神经网络（Addernets）在图像分类上表现出令人印象深刻的性能，只有加法操作，比使用乘法建立的传统卷积神经网络更节能。与分类相比，对通过Addernets降低现代对象探测器的能耗的强烈需求，例如自主驾驶和面部检测。在本文中，我们提出了对物体检测的addernets的实证研究。我们首先揭示了预先训练的加法器骨架中的批量归一化统计，不应冻结，因为Addernets的相对较大的特征方差。此外，我们在颈部中插入更多的快捷方式连接，并设计一个新的特征融合架构，以避免加法器层的稀疏功能。我们展示了广泛的消融研究，探讨了加法器探测器的几种设计选择。与最先进的比较在Coco和Pascal VOC基准上进行。具体而言，所提出的加法器FCOS在Coco Val集上实现了37.8 \％AP，展示了卷积对应物的相当性能，具有约1.4倍的能量减少。

This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8× and 5.5× fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https: //github.com/facebookresearch/SlowFast.

The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10× or 100×? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between 'enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pretraining) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-theart results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10× more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https: //github.com/facebookresearch/SlowFast.

对象检测是用于测试预先训练的网络参数的中央下游任务是否达到益处，例如提高准确度或训练速度。当新架构（如视觉变压器（VIT）模型到达时，物体检测方法的复杂性可以使该基准是非微不足道的。这些困难（例如，架构不相容，慢训练，高记忆消耗，未知的培训公式等）已经阻止了最近通过标准VIT模型进行了基准测试转移学习的研究。在本文中，我们提出了克服这些挑战的培训技术，使得使用标准的VT模型作为面膜R-CNN的骨干。这些工具促进了我们研究的主要目标：我们比较五种Vit初始化，包括最近的最先进的自我监督的学习方法，监督初始化和强大的随机初始化基线。我们的研究结果表明，最近基于掩蔽的无监督学习方法可能是在COCO的令人信服的转移学习改进，将箱子AP增加到4％（绝对）的监督和先前自我监督的预训练方法。此外，基于掩蔽的初始化比例更好，随着模型尺寸的增加而增长的提高。

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers-8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions 1 , where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

我们探索普通的非层次视觉变压器（VIT）作为用于对象检测的骨干网络。该设计使原始的VIT体系结构可以进行微调以进行对象检测，而无需重新设计层次结构的主链以进行预训练。随着微调的最低适应性，我们的纯净背骨检测器可以取得竞争成果。令人惊讶的是，我们观察到：（i）足以从单尺度特征映射（没有常见的FPN设计）构建一个简单的特征金字塔，并且（ii）足以使用窗户注意力（无需转移），很少有帮助跨窗口传播块。凭借普通的VIT骨架作为掩盖自动编码器（MAE），我们的探测器（名为VITDET）可以与先前基于层次结构骨架的先前领先方法竞争，仅使用ImagEnet-1k Pre Pre pre to Coco Dataset上的61.3 ap_box竞争-训练。我们希望我们的研究能够引起人们对普通背骨检测器的研究。 VITDET的代码可在detectron2中获得。

视觉识别的“咆哮20S”开始引入视觉变压器（VITS），这将被取代的Cummnets作为最先进的图像分类模型。另一方面，vanilla vit，当应用于一般计算机视觉任务等对象检测和语义分割时面临困难。它是重新引入多个ConvNet Priors的等级变压器（例如，Swin变压器），使变压器实际上可作为通用视觉骨干网，并在各种视觉任务上展示了显着性能。然而，这种混合方法的有效性仍然在很大程度上归功于变压器的内在优越性，而不是卷积的固有感应偏差。在这项工作中，我们重新审视设计空间并测试纯粹的Convnet可以实现的限制。我们逐渐“现代化”标准Reset朝着视觉变压器的设计设计，并发现几个有助于沿途绩效差异的关键组件。此探索的结果是一个纯粹的ConvNet型号被称为ConvNext。完全由标准的Convnet模块构建，ConvNexts在准确性和可扩展性方面与变压器竞争，实现了87.8％的ImageNet Top-1精度和表现优于COCO检测和ADE20K分割的Swin变压器，同时保持了标准Convnet的简单性和效率。

转移学习的一种常见做法是通过预先培训数据丰富的上游任务来初始化下游模型权重。在对象检测中，特征主链通常用成像网分类器的权重初始化，并在对象检测任务上进行微调。最近的作品表明，在更长的培训方案下，这不是严格必要的，并提供了从头开始训练骨干的食谱。我们研究了这种端到端训练趋势的相反方向：我们表明，一种极端的知识保存形式 - 冻结分类器至关重要的骨干 - 始终改善许多不同的检测模型，并导致可观的资源节省。我们假设并通过实验证实，其余的检测器成分的容量和结构是利用冷冻骨架的关键因素。我们发现的直接应用包括对严重案例的绩效改进，例如检测长尾对象类别以及计算和内存资源节省，这有助于使该领域更容易访问具有更少的计算资源的研究人员。

灵感来自动物视觉系统中的两个基本机制，我们介绍了一种特征变换技术，在深神经网络训练中强加不变性。生成的算法需要较少的参数调整，用初始学习速率1.0提供良好的列车，并且容易地推广到不同的任务。我们使用数据中的本地统计数据强制不变性，以使类似的样本对齐不同的标度。为了加速融合，我们强制使用从批处理中提取的全局统计数据来执行GL（n）-invariance属性，使得梯度下降溶液应保持不变的基础变化。分析分析表明我们所提出的修改需要底层卷积层的计算的5％。在卷积网络和变压器网络上测试，我们提出的技术需要较少的迭代训练，超过所有基线，通过大幅度，无缝工作，对小型和大批量训练，并适用于不同的计算机视觉和语言任务。

本文显示屏蔽的自动化器（MAE）是可扩展的自我监督学习者，用于计算机愿景。我们的MAE方法很简单：我们掩盖输入图像的随机补丁并重建缺失像素。它基于两个核心设计。首先，我们开发一个不对称的编码器解码器架构，其中编码器仅在掩码的可见子集（没有掩码令牌）上，以及重量解码器，该重量解码器从潜像和掩码令牌重建原始图像。其次，我们发现掩蔽了高比例的输入图像，例如，75％，产生非凡和有意义的自我监督任务。耦合这两种设计使我们能够有效且有效地培训大型模型：我们加速培训（3倍或更多）并提高准确性。我们可扩展的方法允许学习概括的高容量模型：例如，Vanilla Vit-Maxim模型在使用Imagenet-1K数据的方法中实现最佳准确性（87.8％）。下游任务中的转移性能优于监督预培训并显示有前途的缩放行为。

Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -from 1 example per class to 1 M total examples. BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB). On small datasets, BiT attains 76.8% on ILSVRC-2012 with 10 examples per class, and 97.0% on CIFAR-10 with 10 examples per class. We conduct detailed analysis of the main components that lead to high transfer performance.