神经网络可以从单个图像中了解视觉世界的内容是什么？虽然它显然不能包含存在的可能对象，场景和照明条件 - 在所有可能的256 ^（3x224x224）224尺寸的方形图像中，它仍然可以在自然图像之前提供强大的。为了分析这一假设，我们通过通过监控掠夺教师的知识蒸馏来制定一种训练神经网络的培训神经网络。有了这个，我们发现上述问题的答案是：“令人惊讶的是，很多”。在定量术语中，我们在CiFar-10/100上找到了94％/ 74％的前1个精度，在想象中，通过将这种方法扩展到音频，84％的语音组合。在广泛的分析中，我们解除了增强，源图像和网络架构的选择，以及在从未见过熊猫的网络中发现“熊猫神经元”。这项工作表明，一个图像可用于推断成千上万的对象类，并激励关于增强和图像的基本相互作用的更新的研究议程。

在实现最先进的性能和在实际应用中负担得起的大型模型之间，计算机视觉的差异越来越大。在本文中，我们解决了这个问题，并显着弥合了这两种模型之间的差距。在我们的实证研究中，我们不一定要提出一种新方法，而是要努力确定一个可靠的有效食谱，以使最先进的大型模型在实践中负担得起。我们证明，当正确执行时，知识蒸馏可以成为减少大型尺寸而不损害其性能的强大工具。特别是，我们发现存在某些隐式设计选择，这可能会严重影响蒸馏的有效性。我们的关键贡献是对这些设计选择的明确识别，这些选择以前在文献中尚未阐明。我们通过一项全面的实证研究备份了我们的发现，在广泛的视觉数据集上展示了令人信服的结果，尤其是获得了最先进的Imagenet Resnet-50模型，该模型可实现82.8％的Top-1准确性。 。

知识蒸馏是一种培训小型学生网络的流行技术，以模仿更大的教师模型，例如网络的集合。我们表明，虽然知识蒸馏可以改善学生泛化，但它通常不得如此普遍地工作：虽然在教师和学生的预测分布之间，甚至在学生容量的情况下，通常仍然存在令人惊讶的差异完美地匹配老师。我们认为优化的困难是为什么学生无法与老师匹配的关键原因。我们还展示了用于蒸馏的数据集的细节如何在学生与老师匹配的紧密关系中发挥作用 - 以及教师矛盾的教师并不总是导致更好的学生泛化。

特征回归是将大型神经网络模型蒸馏到较小的功能回归。我们表明，随着网络架构的简单变化，回归可能会优于自我监督模型的知识蒸馏更复杂的最先进方法。令人惊讶的是，即使仅在蒸馏过程中仅使用并且在下游任务中丢弃时，将多层的Perceptron头部添加到CNN骨架上是有益的。因此，更深的非线性投影可以使用在不改变推理架构和时间的情况下准确地模仿老师。此外，我们利用独立的投影头来同时蒸馏多个教师网络。我们还发现，使用与教师和学生网络的输入相同的弱增强图像辅助蒸馏。Imagenet DataSet上的实验证明了各种自我监督蒸馏环境中提出的变化的功效。

尽管对视频表示学习的自我监督预先预测方法的突出成功，但在未标记的预测数据集很小或源任务（预先训练）中的未标记数据和目标任务中标记的数据（Fineetuning）之间的域差异。为了缓解这些问题，我们提出了一种新的方法来通过基于知识相似性蒸馏，Auxskd的辅助预押阶段补充自我监督预测，以便更好地推广，具有明显较少量的视频数据，例如，动力学-100而不是动力学-400。我们的方法通过捕获未标记的视频数据的段之间的相似信息，将其知识迭代地将其知识蒸发到学生模型。然后，学生模型通过利用此先验知识来解决借口任务。我们还介绍了一种新颖的借口任务，视频段速度预测或VSPP，这需要我们的模型来预测输入视频的随机选择段的播放速度，以提供更可靠的自我监督的表示。我们的实验结果表明，在K100上预先训练时，UCF101和HMDB51数据集的最先进结果卓越。此外，我们表明我们的辅助辅助辅助持久性辅助阶段作为最近的艺术的自我监督方法（例如VideOpace和Rspnet），可以在UCF101和HMDB51上提高结果。我们的代码即将发布。

Jitendra Malik once said, "Supervision is the opium of the AI researcher". Most deep learning techniques heavily rely on extreme amounts of human labels to work effectively. In today's world, the rate of data creation greatly surpasses the rate of data annotation. Full reliance on human annotations is just a temporary means to solve current closed problems in AI. In reality, only a tiny fraction of data is annotated. Annotation Efficient Learning (AEL) is a study of algorithms to train models effectively with fewer annotations. To thrive in AEL environments, we need deep learning techniques that rely less on manual annotations (e.g., image, bounding-box, and per-pixel labels), but learn useful information from unlabeled data. In this thesis, we explore five different techniques for handling AEL.

知识蒸馏（KD）是一种有效的方法，可以将知识从大型“教师”网络转移到较小的“学生”网络。传统的KD方法需要大量标记的培训样本和白盒老师（可以访问参数）才能培训好学生。但是，这些资源并不总是在现实世界应用中获得。蒸馏过程通常发生在我们无法访问大量数据的外部政党方面，并且由于安全性和隐私问题，教师没有披露其参数。为了克服这些挑战，我们提出了一种黑盒子少的KD方法，以培训学生很少的未标记培训样本和一个黑盒老师。我们的主要思想是通过使用混合和有条件的变异自动编码器生成一组不同的分布合成图像来扩展训练集。这些合成图像及其从老师获得的标签用于培训学生。我们进行了广泛的实验，以表明我们的方法在图像分类任务上明显优于最近的SOTA/零射击KD方法。代码和型号可在以下网址找到：https：//github.com/nphdang/fs-bbt

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network's implicit knowledge to guide the learning of a smaller network. At first glance, these two techniques seem very different, however, we found that ``smoothness" is the connecting link between the two and is also a crucial attribute in understanding KD's interplay with mixup. Although many mixup variants and distillation methods have been proposed, much remains to be understood regarding the role of a mixup in knowledge distillation. In this paper, we present a detailed empirical study on various important dimensions of compatibility between mixup and knowledge distillation. We also scrutinize the behavior of the networks trained with a mixup in the light of knowledge distillation through extensive analysis, visualizations, and comprehensive experiments on image classification. Finally, based on our findings, we suggest improved strategies to guide the student network to enhance its effectiveness. Additionally, the findings of this study provide insightful suggestions to researchers and practitioners that commonly use techniques from KD. Our code is available at https://github.com/hchoi71/MIX-KD.

Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the notion of a multimodal versatile network -a network that can ingest multiple modalities and whose representations enable downstream tasks in multiple modalities. In particular, we explore how best to combine the modalities, such that fine-grained representations of the visual and audio modalities can be maintained, whilst also integrating text into a common embedding. Driven by versatility, we also introduce a novel process of deflation, so that the networks can be effortlessly applied to the visual data in the form of video or a static image. We demonstrate how such networks trained on large collections of unlabelled video data can be applied on video, video-text, image and audio tasks. Equipped with these representations, we obtain state-of-the-art performance on multiple challenging benchmarks including UCF101, HMDB51, Kinetics600, Audioset and ESC-50 when compared to previous self-supervised work. Our models are publicly available [1, 2, 3]. * Equal contribution. † Work done during an internship at DeepMind. 34th Conference on Neural Information Processing Systems (NeurIPS 2020),

Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher accuracy at greater computational cost, but changing the patch size typically requires retraining the model. In this paper, we demonstrate that simply randomizing the patch size at training time leads to a single set of weights that performs well across a wide range of patch sizes, making it possible to tailor the model to different compute budgets at deployment time. We extensively evaluate the resulting model, which we call FlexiViT, on a wide range of tasks, including classification, image-text retrieval, open-world detection, panoptic segmentation, and semantic segmentation, concluding that it usually matches, and sometimes outperforms, standard ViT models trained at a single patch size in an otherwise identical setup. Hence, FlexiViT training is a simple drop-in improvement for ViT that makes it easy to add compute-adaptive capabilities to most models relying on a ViT backbone architecture. Code and pre-trained models are available at https://github.com/google-research/big_vision

自我监督的预制是自然语言处理模型的首选方法，在许多愿景任务中迅速获得普及。最近，自我监督的预借鉴已经显示出胜过许多下游视觉应用的预测，标志着该地区的里程碑。这种优越性归因于传达多个概念的训练图像的不完全标记的负面影响，而是使用单个主要类标签进行注释。虽然自我监督的学习（SSL）原则上没有这种限制，但促进SSL的借口任务的选择是通过向单个概念输出驱动学习过程来实现这种缺点。本研究旨在调查在不使用标签的情况下建模图像中存在的所有概念的可能性。在这方面，所提出的SSL帧工作MC-SSL0.0是迈向多概念自我监督学习（MC-SSL）的步骤，其超出了在图像中建模的单一主导标签，以有效地利用来自所有概念的所有概念在里面。 MC-SSL0.0由两个核心设计概念，组屏蔽模型学习和学习伪概念，用于使用势头（教师学生）框架的数据令牌。多标签和多类图像分类下游任务的实验结果表明，MC-SSL0.0不仅超越了现有的SSL方法，而且超越了监督转移学习。源代码将公开可供社区培训更大的语料库。

Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a systematic and extensive overview of the state of the art, and a common benchmark to allow for objective comparisons between published methods. This article addresses both issues. First, we systematically organize and connect past studies to consolidate a community that is currently fragmented and scattered. Second, we propose a common benchmark that allows for an objective comparison of approaches. It consists of five datasets spanning various domains (e.g., natural images, medical imagery, satellite data) and data types (RGB, grayscale, multispectral). We use this benchmark to re-evaluate the standard cross-entropy baseline and ten existing methods published between 2017 and 2021 at renowned venues. Surprisingly, we find that thorough hyper-parameter tuning on held-out validation data results in a highly competitive baseline and highlights a stunted growth of performance over the years. Indeed, only a single specialized method dating back to 2019 clearly wins our benchmark and outperforms the baseline classifier.

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled video clips. XKD is trained with two pseudo tasks. First, masked data reconstruction is performed to learn modality-specific representations. Next, self-supervised cross-modal knowledge distillation is performed between the two modalities through teacher-student setups to learn complementary information. To identify the most effective information to transfer and also to tackle the domain gap between audio and visual modalities which could hinder knowledge transfer, we introduce a domain alignment strategy for effective cross-modal distillation. Lastly, to develop a general-purpose solution capable of handling both audio and visual streams, a modality-agnostic variant of our proposed framework is introduced, which uses the same backbone for both audio and visual modalities. Our proposed cross-modal knowledge distillation improves linear evaluation top-1 accuracy of video action classification by 8.4% on UCF101, 8.1% on HMDB51, 13.8% on Kinetics-Sound, and 14.2% on Kinetics400. Additionally, our modality-agnostic variant shows promising results in developing a general-purpose network capable of handling different data streams. The code is released on the project website.

Vision Transformer（VIT）最近由于其出色的模型功能而引起了计算机视觉的极大关注。但是，大多数流行的VIT模型都有大量参数，从而限制了其在资源有限的设备上的适用性。为了减轻这个问题，我们提出了Tinyvit，这是一个新的小型，有效的小型视觉变压器，并通过我们提议的快速蒸馏框架在大型数据集上预处理。核心思想是将知识从大型模型转移到小型模型，同时使小型模型能够获得大量预处理数据的股息。更具体地说，我们在预训练期间应用蒸馏进行知识转移。大型教师模型的徽标被稀疏并提前存储在磁盘中，以节省内存成本和计算开销。微小的学生变形金刚自动从具有计算和参数约束的大型审计模型中缩小。全面的实验证明了TinyVit的功效。它仅具有21m参数的Imagenet-1k上的前1个精度为84.8％，与在Imagenet-21K上预读的SWIN-B相当，而使用较少的参数则使用了4.2倍。此外，增加图像分辨率，TinyVit可以达到86.5％的精度，仅使用11％参数，比SWIN-L略好。最后但并非最不重要的一点是，我们在各种下游任务上展示了TinyVit的良好转移能力。代码和型号可在https://github.com/microsoft/cream/tree/main/tinyvit上找到。

We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, it improves ImageNet-A top-1 accuracy from 61.0% to 83.7%, reduces ImageNet-C mean corruption error from 45.7 to 28.3, and reduces ImageNet-P mean flip rate from 27.8 to 12.2.Noisy Student Training extends the idea of self-training and distillation with the use of equal-or-larger student models and noise added to the student during learning. On Im-ageNet, we first train an EfficientNet model on labeled images and use it as a teacher to generate pseudo labels for 300M unlabeled images. We then train a larger Efficient-Net as a student model on the combination of labeled and pseudo labeled images. We iterate this process by putting back the student as the teacher. During the learning of the student, we inject noise such as dropout, stochastic depth, and data augmentation via RandAugment to the student so that the student generalizes better than the teacher. 1 * This work was conducted at Google.

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.

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These highperforming vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.In this work, we produce competitive convolution-free transformers by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.