自我监督学习的一个重要目标是使模型预训练能够从几乎无限的数据中受益。但是，一种最近变得流行的方法，即掩盖图像建模（MIM），被怀疑无法从较大的数据中受益。在这项工作中，我们通过广泛的实验打破了这一误解，数据量表从10 \％imagenet-1k到完整的Imagenet-22K，型号的尺寸从4,900万到10亿，培训长度从125k迭代到500k迭代迭代范围不等。我们的研究表明：（i）蒙版的图像建模也要求对较大的数据进行要求。我们观察到，非常大的模型被相对较小的数据过度。 （ii）培训的时间长度。接受掩盖图像建模训练的大型模型可以从更多的数据中受益，并具有更长的培训。 （iii）预训练中的验证损失是衡量模型在多个任务上进行微调的表现的好指标。该观察结果使我们能够预先评估预训练的模型，而无需对下游任务进行昂贵的试用和错误评估。我们希望我们的发现能够从缩放能力方面提高对蒙版图像建模的理解。

蒙版的图像建模（MIM）学习具有非常好的微调性能的表示形式，掩盖了先前普遍的预训练方法，例如图像分类，实例对比度学习和图像文本对齐。在本文中，我们表明，通过以功能蒸馏（FD）形式进行简单的后处理，可以显着改善这些预训练方法的下部微调性能。功能蒸馏将旧表示形式转换为具有一些理想属性的新表示形式，就像MIM产生的表示一样。这些属性总共称为优化友好性，通过一组与注意力和优化相关的诊断工具来识别和分析。借助这些属性，新表示表现出强烈的微调性能。具体而言，对比度的自我监督学习方法在微调方面具有竞争力，就像最先进的蒙版图像建模（MIM）算法一样。剪辑模型的微调性能也得到了显着改善，夹子VIT-L模型达到\ TextBf {89.0％} TOP-1的ImagEnet-1K分类精度。在30亿参数SWINV2-G模型上，ADE20K语义分割的微调精度通过+1.5 miou提高到\ textbf {61.4 miou}，创建了新记录。更重要的是，我们的工作为未来的研究提供了一种方法，可以将更多的精力集中在学习表现的通用性和可扩展性上，而不会与优化友好性相处，因为它可以很容易地增强。该代码将在https://github.com/swintransformer/feature-distillation上找到。

本文介绍了Simmim，这是一个简单的蒙面图像建模框架。我们在没有特殊设计的情况下简化了最近提出的相关方法，例如通过离散VAE或聚类的块状掩蔽和令牌化。要研究蒙版图像建模任务学习良好的表示，我们系统地研究了我们框架中的主要组成部分，并发现每个组件的简单设计揭示了非常强烈的表示学习性能：1）用中等的输入图像随机掩蔽输入图像大型蒙面贴片尺寸（例如，32）进行了强大的文本前任务; 2）通过直接回归预测RGB值的原始像素不比具有复杂设计的补丁分类方法更差; 3）预测头可以像线性层一样光，性能比较重的形式更差。使用VIT-B，我们的方法通过预训练在此数据集上进行预培训，我们的方法在ImageNet-1K上实现了83.8％的精细调整精度，超过了以前最佳方法+ 0.6％。当应用于大约6.5亿参数的更大模型时，SwinV2-H，它在Imagenet-1K上使用Imagenet-1K数据实现了87.1％的前1个精度。我们还利用这种方法来促进3B模型（SWINV2-G）的培训，比以前的实践中的数据减少40美元，我们在四个代表性视觉基准上实现了最先进的。代码和模型将在https://github.com/microsoft/simmim公开使用。

我们提出了用于将Swin变压器缩放到3亿参数的技术，并使其能够使用高达1,536美元的图像培训1,536美元。通过缩放容量和分辨率，Swin变压器在四个代表视觉基准上设置新记录：84.0％的Top-1在Imagenet-V2图像分类准确度，63.1 / 54.4盒/掩模地图上的Coco对象检测，59.9 Miou在Ade20K语义细分中，在动力学-400视频动作分类上的86.8％的前1个精度。我们的技术通常适用于缩放视觉模型，这尚未广泛探索为NLP语言模型，部分原因是培训和应用中的困难：1）视觉模型经常面临规模的不稳定问题，2）许多下游愿景任务需要高分辨率图像或窗口，并且目前尚不清楚如何有效地将模型在低分辨率上预先培训到更高分辨率。当图像分辨率高时，GPU存储器消耗也是一个问题。为了解决这些问题，我们提出了几种技术，通过使用Swin Transformer作为案例研究来说明：1）归一化技术和缩放的余弦注意力，提高大视觉模型的稳定性; 2）一种日志间隔的连续位置偏置技术，以有效地将在低分辨率图像和窗口预先训练的模型转移到其更高分辨率的对应物。此外，我们分享了我们的关键实施细节，导致GPU内存消耗的大量节省，从而使得用常规GPU培训大型视觉模型可行。使用这些技术和自我监督的预训练，我们成功培训了强大的3B往返变压器模型，并有效地将其转移到涉及高分辨率图像或窗口的各种视觉任务，实现了各种最先进的准确性基准。

以前的周期 - 一致性对应学习方法通​​常利用图像补丁进行培训。在本文中，我们介绍了一种完全卷积的方法，它对推理过程更简单，更加连贯。在直接应用全面卷积训练的同时，在模型崩溃中，我们研究了这种崩溃现象背后的下划线原因，表明像素的绝对位置提供了易于完成循环一致的快捷方式，这阻碍了有意义的视觉表现的学习。为了打破这种绝对的位置捷径，我们建议将不同的作物应用于前向和后向框架，并采用特征翘曲来建立相同框架两种作物之间的对应关系。前者技术在前后跟踪处强制执行相应的像素以具有不同的绝对位置，并且后者有效地阻止前后轨道之间的快捷方式。在三个标签传播基准台上进行姿势跟踪，面部地标跟踪和视频对象分割，我们的方法在很大程度上提高了香草完全卷积循环一致性方法的结果，与自我监督最先进的方法相比，实现了非常竞争力的表现。我们的培训模型和代码可用于\ url {https://github.com/steve-tod/stfc3}。

Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions. In this paper, we introduce pixel-level pretext tasks for learning dense feature representations. The first task directly applies contrastive learning at the pixel level. We additionally propose a pixel-to-propagation consistency task that produces better results, even surpassing the state-of-the-art approaches by a large margin. Specifically, it achieves 60.2 AP, 41.4 / 40.5 mAP and 77.2 mIoU when transferred to Pascal VOC object detection (C4), COCO object detection (FPN / C4) and Cityscapes semantic segmentation using a ResNet-50 backbone network, which are 2.6 AP, 0.8 / 1.0 mAP and 1.0 mIoU better than the previous best methods built on instance-level contrastive learning. Moreover, the pixel-level pretext tasks are found to be effective for pretraining not only regular backbone networks but also head networks used for dense downstream tasks, and are complementary to instance-level contrastive methods. These results demonstrate the strong potential of defining pretext tasks at the pixel level, and suggest a new path forward in unsupervised visual representation learning. Code is available at https://github.com/zdaxie/PixPro.

The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling visual elements with varying spatial distributions. This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference. A network built with local relation layers, called the Local Relation Network (LR-Net), is found to provide greater modeling capacity than its counterpart built with regular convolution on large-scale recognition tasks such as ImageNet classification.

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

A step-search sequential quadratic programming method is proposed for solving nonlinear equality constrained stochastic optimization problems. It is assumed that constraint function values and derivatives are available, but only stochastic approximations of the objective function and its associated derivatives can be computed via inexact probabilistic zeroth- and first-order oracles. Under reasonable assumptions, a high-probability bound on the iteration complexity of the algorithm to approximate first-order stationarity is derived. Numerical results on standard nonlinear optimization test problems illustrate the advantages and limitations of our proposed method.

Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this issue, we introduce a conceptually simple yet learning-efficient MIM training scheme, termed Disjoint Masking with Joint Distillation (DMJD). For disjoint masking (DM), we sequentially sample multiple masked views per image in a mini-batch with the disjoint regulation to raise the usage of tokens for reconstruction in each image while keeping the masking rate of each view. For joint distillation (JD), we adopt a dual branch architecture to respectively predict invisible (masked) and visible (unmasked) tokens with superior learning targets. Rooting in orthogonal perspectives for training efficiency improvement, DM and JD cooperatively accelerate the training convergence yet not sacrificing the model generalization ability. Concretely, DM can train ViT with half of the effective training epochs (3.7 times less time-consuming) to report competitive performance. With JD, our DMJD clearly improves the linear probing classification accuracy over ConvMAE by 5.8%. On fine-grained downstream tasks like semantic segmentation, object detection, etc., our DMJD also presents superior generalization compared with state-of-the-art SSL methods. The code and model will be made public at https://github.com/mx-mark/DMJD.