Self-supervised visual representation learning has seen huge progress recently, but no large scale evaluation has compared the many models now available. We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction. We compare their performance to a supervised baseline and show that on most tasks the best self-supervised models outperform supervision, confirming the recently observed trend in the literature. We find ImageNet Top-1 accuracy to be highly correlated with transfer to many-shot recognition, but increasingly less so for few-shot, object detection and dense prediction. No single self-supervised method dominates overall, suggesting that universal pre-training is still unsolved. Our analysis of features suggests that top self-supervised learners fail to preserve colour information as well as supervised alternatives, but tend to induce better classifier calibration, and less attentive overfitting than supervised learners.

我们提出了一种适用于半全球任务的自学学习（SSL）方法，例如对象检测和语义分割。我们通过在训练过程中最大程度地减少像素级局部对比度（LC）损失，代表了同一图像转换版本的相应图像位置之间的局部一致性。可以将LC-LOSS添加到以最小开销的现有自我监督学习方法中。我们使用可可，Pascal VOC和CityScapes数据集评估了两个下游任务的SSL方法 - 对象检测和语义细分。我们的方法的表现优于现有的最新SSL方法可可对象检测的方法1.9％，Pascal VOC检测1.4％，而CityScapes Sementation则为0.6％。

自我监督的学习是一个强大的范例，用于在未标记的图像上学习。基于实例匹配的大量有效的新方法依赖于数据增强来推动学习，这些方法达成了优化流行识别基准的增强方案的粗略协议。但是，有强有力的理由可疑计算机视觉中的不同任务需要对不同（IN）差异进行编码的功能，因此可能需要不同的增强策略。在本文中，我们衡量了对比方法学到的修正学知识，并确认他们确实学会了与使用的增强的不变性，进一步表明，这一不变性大大转移到与姿势和照明的相关真实变化的变化很大程度上转移。我们展示了学习的InorRARCES强烈影响下游任务性能，并确认不同的下游任务从极性相反（IN）差异中受益，导致使用标准增强策略时的性能损失。最后，我们证明，具有互补的修正条件的表现简单融合可确保对所考虑的所有不同下游任务进行广泛的可转换性。

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74.3% top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and 79.6% with a larger ResNet. We show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks. Our implementation and pretrained models are given on GitHub. 3 * Equal contribution; the order of first authors was randomly selected.

最近自我监督学习成功的核心组成部分是裁剪数据增强，其选择要在自我监督损失中用作正视图的图像的子区域。底层假设是给定图像的随机裁剪和调整大小的区域与感兴趣对象的信息共享信息，其中学习的表示将捕获。这种假设在诸如想象网的数据集中大多满足，其中存在大，以中心为中心的对象，这很可能存在于完整图像的随机作物中。然而，在诸如OpenImages或Coco的其他数据集中，其更像是真实世界未保健数据的代表，通常存在图像中的多个小对象。在这项工作中，我们表明，基于通常随机裁剪的自我监督学习在此类数据集中表现不佳。我们提出用从对象提案算法获得的作物取代一种或两种随机作物。这鼓励模型学习对象和场景级别语义表示。使用这种方法，我们调用对象感知裁剪，导致对分类和对象检测基准的场景裁剪的显着改进。例如，在OpenImages上，我们的方法可以使用基于Moco-V2的预训练来实现8.8％的提高8.8％地图。我们还显示了对Coco和Pascal-Voc对象检测和分割任务的显着改善，通过最先进的自我监督的学习方法。我们的方法是高效，简单且通用的，可用于最现有的对比和非对比的自我监督的学习框架。

Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform better on ImageNet necessarily perform better on other vision tasks. However, this hypothesis has never been systematically tested. Here, we compare the performance of 16 classification networks on 12 image classification datasets. We find that, when networks are used as fixed feature extractors or fine-tuned, there is a strong correlation between ImageNet accuracy and transfer accuracy (r = 0.99 and 0.96, respectively). In the former setting, we find that this relationship is very sensitive to the way in which networks are trained on ImageNet; many common forms of regularization slightly improve ImageNet accuracy but yield penultimate layer features that are much worse for transfer learning. Additionally, we find that, on two small fine-grained image classification datasets, pretraining on ImageNet provides minimal benefits, indicating the learned features from Ima-geNet do not transfer well to fine-grained tasks. Together, our results show that ImageNet architectures generalize well across datasets, but ImageNet features are less general than previously suggested.

我们专注于更好地理解增强不变代表性学习的关键因素。我们重新访问moco v2和byol，并试图证明以下假设的真实性：不同的框架即使具有相同的借口任务也会带来不同特征的表示。我们建立了MoCo V2和BYOL之间公平比较的第一个基准，并观察：（i）复杂的模型配置使得可以更好地适应预训练数据集； （ii）从实现竞争性转移表演中获得的预训练和微调阻碍模型的优化策略不匹配。鉴于公平的基准，我们进行进一步的研究并发现网络结构的不对称性赋予对比框架在线性评估协议下正常工作，同时可能会损害长尾分类任务的转移性能。此外，负样本并不能使模型更明智地选择数据增强，也不会使不对称网络结构结构。我们相信我们的发现为将来的工作提供了有用的信息。

尽管最近通过剩余网络的代表学习中的自我监督方法取得了进展，但它们仍然对ImageNet分类基准进行了高度的监督学习，限制了它们在性能关键设置中的适用性。在MITROVIC等人的现有理论上洞察中建立2021年，我们提出了RELICV2，其结合了明确的不变性损失，在各种适当构造的数据视图上具有对比的目标。 Relicv2在ImageNet上实现了77.1％的前1个分类准确性，使用线性评估使用Reset50架构和80.6％，具有较大的Reset型号，优于宽边缘以前的最先进的自我监督方法。最值得注意的是，RelicV2是使用一系列标准Reset架构始终如一地始终优先于类似的对比较中的监督基线的第一个表示学习方法。最后，我们表明，尽管使用Reset编码器，Relicv2可与最先进的自我监控视觉变压器相媲美。

跟踪视频感兴趣的对象是计算机视觉中最受欢迎和最广泛应用的问题之一。然而，随着年的几年，寒武纪的用例和基准已经将问题分散在多种不同的实验设置中。因此，文献也已经分散，现在社区提出的新方法通常是专门用于仅适合一个特定的设置。要了解在多大程度上，这项专业化是必要的，在这项工作中，我们展示了UnitRack，一个解决方案来解决同一框架内的五个不同任务。 Unitrack由单一和任务不可知的外观模型组成，可以以监督或自我监督的方式学习，以及解决个人任务的多个`“头”，并且不需要培训。我们展示了在该框架内可以解决的大多数跟踪任务，并且可以成功地成功地使用相同的外观模型来获得对针对考虑大多数任务的专业方法具有竞争力的结果。该框架还允许我们分析具有最新自我监督方法获得的外观模型，从而扩展了他们的评估并与更大种类的重要问题进行比较。

对比自我监督的学习已经超越了许多下游任务的监督预测，如分割和物体检测。但是，当前的方法仍然主要应用于像想象成的策划数据集。在本文中，我们首先研究数据集中的偏差如何影响现有方法。我们的研究结果表明，目前的对比方法令人惊讶地工作：（i）对象与场景为中心，（ii）统一与长尾和（iii）一般与域特定的数据集。其次，鉴于这种方法的一般性，我们尝试通过微小的修改来实现进一步的收益。我们展示了学习额外的修正 - 通过使用多尺度裁剪，更强的增强和最近的邻居 - 改善了表示。最后，我们观察Moco在用多作物策略训练时学习空间结构化表示。表示可以用于语义段检索和视频实例分段，而不会FineTuning。此外，结果与专门模型相提并论。我们希望这项工作将成为其他研究人员的有用研究。代码和模型可在https://github.com/wvanganebleke/revisiting-contrastive-ssl上获得。

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.

在计算病理学工作流程中检测和分裂ObjectSwithinWholesLideImagesis。自我监督学习（SSL）吸引了这种重度注释的任务。尽管自然图像的密集任务具有广泛的基准，但不幸的是，在当前的病理学作品中，此类研究仍然没有。我们的论文打算缩小这一差距。我们首先基于病理图像中密集预测任务的代表性SSL方法。然后，我们提出了概念对比学习（结论），这是密集预训练的SSL框架。我们探讨了结论如何使用不同来源提供的概念，并最终提出了一种简单的无依赖性概念生成方法，该方法不依赖于外部分割算法或显着检测模型。广泛的实验表明，在不同环境中，结论比以前的最新SSL方法具有优势。沿着我们的探索，我们弥补了几个重要而有趣的组成部分，这有助于致力于病理图像的密集预训练。我们希望这项工作可以提供有用的数据点，并鼓励社区为感兴趣的问题进行结论预培训。代码可用。

Computational pathology can lead to saving human lives, but models are annotation hungry and pathology images are notoriously expensive to annotate. Self-supervised learning has shown to be an effective method for utilizing unlabeled data, and its application to pathology could greatly benefit its downstream tasks. Yet, there are no principled studies that compare SSL methods and discuss how to adapt them for pathology. To address this need, we execute the largest-scale study of SSL pre-training on pathology image data, to date. Our study is conducted using 4 representative SSL methods on diverse downstream tasks. We establish that large-scale domain-aligned pre-training in pathology consistently out-performs ImageNet pre-training in standard SSL settings such as linear and fine-tuning evaluations, as well as in low-label regimes. Moreover, we propose a set of domain-specific techniques that we experimentally show leads to a performance boost. Lastly, for the first time, we apply SSL to the challenging task of nuclei instance segmentation and show large and consistent performance improvements under diverse settings.

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning (DenseCL), which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images.Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin. Specifically, over the strong MoCo-v2 baseline, our method achieves significant improvements of 2.0% AP on PASCAL VOC object detection, 1.1% AP on COCO object detection, 0.9% AP on COCO instance segmentation, 3.0% mIoU on PASCAL VOC semantic segmentation and 1.8% mIoU on Cityscapes semantic segmentation.

标记数据通常昂贵且耗时，特别是对于诸如对象检测和实例分割之类的任务，这需要对图像的密集标签进行密集的标签。虽然几张拍摄对象检测是关于培训小说中的模型（看不见的）对象类具有很少的数据，但它仍然需要在许多标记的基础（见）类的课程上进行训练。另一方面，自我监督的方法旨在从未标记数据学习的学习表示，该数据转移到诸如物体检测的下游任务。结合几次射击和自我监督的物体检测是一个有前途的研究方向。在本调查中，我们审查并表征了几次射击和自我监督对象检测的最新方法。然后，我们给我们的主要外卖，并讨论未来的研究方向。https://gabrielhuang.github.io/fsod-survey/的项目页面

自我监督学习的最新进展证明了多种视觉任务的有希望的结果。高性能自我监督方法中的一个重要成分是通过培训模型使用数据增强，以便在嵌入空间附近的相同图像的不同增强视图。然而，常用的增强管道整体地对待图像，忽略图像的部分的语义相关性-e.g。主题与背景 - 这可能导致学习杂散相关性。我们的工作通过调查一类简单但高度有效的“背景增强”来解决这个问题，这鼓励模型专注于语义相关内容，劝阻它们专注于图像背景。通过系统的调查，我们表明背景增强导致在各种任务中跨越一系列最先进的自我监督方法（MOCO-V2，BYOL，SWAV）的性能大量改进。 $ \ SIM $ + 1-2％的ImageNet收益，使得与监督基准的表现有关。此外，我们发现有限标签设置的改进甚至更大（高达4.2％）。背景技术增强还改善了许多分布换档的鲁棒性，包括天然对抗性实例，想象群-9，对抗性攻击，想象成型。我们还在产生了用于背景增强的显着掩模的过程中完全无监督的显着性检测进展。

Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or "views") of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a "swapped" prediction mechanism where we predict the code of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements. We validate our findings by achieving 75.3% top-1 accuracy on ImageNet with ResNet-50, as well as surpassing supervised pretraining on all the considered transfer tasks.

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.

对比的自我监督学习在很大程度上缩小了对想象成的预先训练的差距。然而，它的成功高度依赖于想象成的以对象形象，即相同图像的不同增强视图对应于相同的对象。当预先训练在具有许多物体的更复杂的场景图像上，如此重种策划约束会立即不可行。为了克服这一限制，我们介绍了对象级表示学习（ORL），这是一个新的自我监督的学习框架迈向场景图像。我们的主要洞察力是利用图像级自我监督的预培训作为发现对象级语义对应之前的，从而实现了从场景图像中学习的对象级表示。对Coco的广泛实验表明，ORL显着提高了自我监督学习在场景图像上的性能，甚至超过了在几个下游任务上的监督Imagenet预训练。此外，当可用更加解标的场景图像时，ORL提高了下游性能，证明其在野外利用未标记数据的巨大潜力。我们希望我们的方法可以激励未来的研究从场景数据的更多通用无人监督的代表。

Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images apart, one can train highly transferable visual representations. As revealed by recent studies, heavy data augmentation and large sets of negatives are both crucial in learning such representations. At the same time, data mixing strategies, either at the image or the feature level, improve both supervised and semi-supervised learning by synthesizing novel examples, forcing networks to learn more robust features. In this paper, we argue that an important aspect of contrastive learning, i.e. the effect of hard negatives, has so far been neglected. To get more meaningful negative samples, current top contrastive self-supervised learning approaches either substantially increase the batch sizes, or keep very large memory banks; increasing memory requirements, however, leads to diminishing returns in terms of performance. We therefore start by delving deeper into a top-performing framework and show evidence that harder negatives are needed to facilitate better and faster learning. Based on these observations, and motivated by the success of data mixing, we propose hard negative mixing strategies at the feature level, that can be computed on-the-fly with a minimal computational overhead. We exhaustively ablate our approach on linear classification, object detection, and instance segmentation and show that employing our hard negative mixing procedure improves the quality of visual representations learned by a state-of-the-art self-supervised learning method.Project page: https://europe.naverlabs.com/mochi 34th Conference on Neural Information Processing Systems (NeurIPS 2020),