Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to distill better from a stronger teacher. We empirically find that the discrepancy of predictions between the student and a stronger teacher may tend to be fairly severer. As a result, the exact match of predictions in KL divergence would disturb the training and make existing methods perform poorly. In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly. Besides, considering that different instances have different semantic similarities to each class, we also extend this relational match to the intra-class level. Our method is simple yet practical, and extensive experiments demonstrate that it adapts well to various architectures, model sizes and training strategies, and can achieve state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at: https://github.com/hunto/DIST_KD .

知识蒸馏（KD）在将学习表征从大型模型（教师）转移到小型模型（学生）方面表现出非常有希望的能力。但是，随着学生和教师之间的容量差距变得更大，现有的KD方法无法获得更好的结果。我们的工作表明，“先验知识”对KD至关重要，尤其是在应用大型老师时。特别是，我们提出了动态的先验知识（DPK），该知识将教师特征的一部分作为特征蒸馏之前的先验知识。这意味着我们的方法还将教师的功能视为“输入”，而不仅仅是``目标''。此外，我们根据特征差距动态调整训练阶段的先验知识比率，从而引导学生在适当的困难中。为了评估所提出的方法，我们对两个图像分类基准（即CIFAR100和Imagenet）和一个对象检测基准（即MS Coco）进行了广泛的实验。结果表明，在不同的设置下，我们方法在性能方面具有优势。更重要的是，我们的DPK使学生模型的表现与教师模型的表现呈正相关，这意味着我们可以通过应用更大的教师进一步提高学生的准确性。我们的代码将公开用于可重复性。

最近对知识蒸馏的研究发现，组合来自多位教师或学生的“黑暗知识”是有助于为培训创造更好的软目标，但以更大的计算和/或参数的成本为本。在这项工作中，我们通过在同一批量中传播和集合其他样本的知识来提供批处理知识合奏（烘焙）以生产用于锚固图像的精细柔软目标。具体地，对于每个感兴趣的样本，根据采样间的亲和力加权知识的传播，其与当前网络一起估计。然后可以集合传播的知识以形成更好的蒸馏靶。通过这种方式，我们的烘焙框架只通过单个网络跨多个样本进行在线知识。与现有知识合并方法相比，它需要最小的计算和内存开销。广泛的实验表明，轻质但有效的烘烤始终如一地提升多个数据集上各种架构的分类性能，例如，在想象网上的显着+ 0.7％的VINE-T的增益，只有+ 1.5％计算开销和零附加参数。烘焙不仅改善了Vanilla基线，还超越了所有基准的单一网络最先进。

最先进的蒸馏方法主要基于中间层的深层特征，而logit蒸馏的重要性被极大地忽略了。为了提供研究逻辑蒸馏的新观点，我们将经典的KD损失重新分为两个部分，即目标类知识蒸馏（TCKD）和非目标类知识蒸馏（NCKD）。我们凭经验研究并证明了这两个部分的影响：TCKD转移有关训练样本“难度”的知识，而NCKD是Logit蒸馏起作用的重要原因。更重要的是，我们揭示了经典的KD损失是一种耦合的配方，该配方抑制了NCKD的有效性，并且（2）限制了平衡这两个部分的灵活性。为了解决这些问题，我们提出了脱钩的知识蒸馏（DKD），使TCKD和NCKD能够更有效，更灵活地发挥其角色。与基于功能的复杂方法相比，我们的DKD可相当甚至更好的结果，并且在CIFAR-100，ImageNet和MS-Coco数据集上具有更好的培训效率，用于图像分类和对象检测任务。本文证明了Logit蒸馏的巨大潜力，我们希望它对未来的研究有所帮助。该代码可从https://github.com/megvii-research/mdistiller获得。

In real teaching scenarios, an excellent teacher always teaches what he (or she) is good at but the student is not. This method gives the student the best assistance in making up for his (or her) weaknesses and becoming a good one overall. Enlightened by this, we introduce the approach to the knowledge distillation framework and propose a data-based distillation method named ``Teaching what you Should Teach (TST)''. To be specific, TST contains a neural network-based data augmentation module with the priori bias, which can assist in finding what the teacher is good at while the student are not by learning magnitudes and probabilities to generate suitable samples. By training the data augmentation module and the generalized distillation paradigm in turn, a student model that has excellent generalization ability can be created. To verify the effectiveness of TST, we conducted extensive comparative experiments on object recognition (CIFAR-100 and ImageNet-1k), detection (MS-COCO), and segmentation (Cityscapes) tasks. As experimentally demonstrated, TST achieves state-of-the-art performance on almost all teacher-student pairs. Furthermore, we conduct intriguing studies of TST, including how to solve the performance degradation caused by the stronger teacher and what magnitudes and probabilities are needed for the distillation framework.

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature. Specifically, following an easy-to-hard curriculum, we gradually increase the distillation loss w.r.t. the temperature, leading to increased distillation difficulty in an adversarial manner. As an easy-to-use plug-in technique, CTKD can be seamlessly integrated into existing knowledge distillation frameworks and brings general improvements at a negligible additional computation cost. Extensive experiments on CIFAR-100, ImageNet-2012, and MS-COCO demonstrate the effectiveness of our method. Our code is available at https://github.com/zhengli97/CTKD.

知识蒸馏（KD）已广泛发展并增强了各种任务。经典的KD方法将KD损失添加到原始的跨熵（CE）损失中。我们尝试分解KD损失，以探索其与CE损失的关系。令人惊讶的是，我们发现它可以被视为CE损失和额外损失的组合，其形式与CE损失相同。但是，我们注意到额外的损失迫使学生学习教师绝对概率的相对可能性。此外，这两个概率的总和是不同的，因此很难优化。为了解决这个问题，我们修改了配方并提出分布式损失。此外，我们将教师的目标输出作为软目标，提出软损失。结合软损失和分布式损失，我们提出了新的KD损失（NKD）。此外，我们将学生的目标输出稳定，将其视为无需教师的培训的软目标，并提出了无教师的新KD损失（TF-NKD）。我们的方法在CIFAR-100和Imagenet上实现了最先进的性能。例如，以Resnet-34为老师，我们将Imagenet TOP-1的RESNET18的TOP-1精度从69.90％提高到71.96％。在没有教师的培训中，Mobilenet，Resnet-18和Swintransformer-tiny的培训占70.04％，70.76％和81.48％，分别比基线高0.83％，0.86％和0.30％。该代码可在https://github.com/yzd-v/cls_kd上找到。

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approach to these problems, minimizes the KL divergence between the probabilistic outputs of a teacher and student network. We demonstrate that this objective ignores important structural knowledge of the teacher network. This motivates an alternative objective by which we train a student to capture significantly more information in the teacher's representation of the data. We formulate this objective as contrastive learning. Experiments demonstrate that our resulting new objective outperforms knowledge distillation and other cutting-edge distillers on a variety of knowledge transfer tasks, including single model compression, ensemble distillation, and cross-modal transfer. Our method sets a new state-of-the-art in many transfer tasks, and sometimes even outperforms the teacher network when combined with knowledge distillation.

最初引入了知识蒸馏，以利用来自单一教师模型的额外监督为学生模型培训。为了提高学生表现，最近的一些变体试图利用多个教师利用不同的知识来源。然而，现有研究主要通过对多种教师预测的平均或将它们与其他无标签策略相结合，将知识集成在多种来源中，可能在可能存在低质量的教师预测存在中误导学生。为了解决这个问题，我们提出了信心感知的多教师知识蒸馏（CA-MKD），该知识蒸馏（CA-MKD）在地面真理标签的帮助下，适用于每个教师预测的样本明智的可靠性，与那些接近单热的教师预测标签分配了大量的重量。此外，CA-MKD包含中间层，以进一步提高学生表现。广泛的实验表明，我们的CA-MKD始终如一地优于各种教师学生架构的所有最先进的方法。

与常规知识蒸馏（KD）不同，自我KD允许网络在没有额外网络的任何指导的情况下向自身学习知识。本文提议从图像混合物（Mixskd）执行自我KD，将这两种技术集成到统一的框架中。 Mixskd相互蒸馏以图形和概率分布在随机的原始图像和它们的混合图像之间以有意义的方式。因此，它通过对混合图像进行监督信号进行建模来指导网络学习跨图像知识。此外，我们通过汇总多阶段功能图来构建一个自学老师网络，以提供软标签以监督骨干分类器，从而进一步提高自我增强的功效。图像分类和转移学习到对象检测和语义分割的实验表明，混合物KD优于其他最先进的自我KD和数据增强方法。该代码可在https://github.com/winycg/self-kd-lib上找到。

尽管深层神经网络在各种任务中取得了巨大的成功，但它们不断增加的规模也为部署带来了重要的开销。为了压缩这些模型，提出了知识蒸馏将知识从笨拙（教师）网络转移到轻量级（学生）网络中。但是，老师的指导并不总是改善学生的概括，尤其是当学生和老师之间的差距很大时。以前的作品认为，这是由于老师的高确定性，导致更难适应的标签。为了软化这些标签，我们提出了一种修剪方法，称为预测不确定性扩大（PRUE），以简化教师。具体而言，我们的方法旨在减少教师对数据的确定性，从而为学生产生软预测。我们从经验上研究了提出的方法通过在CIFAR-10/100，Tiny-Imagenet和Imagenet上实验的实验的有效性。结果表明，接受稀疏教师培训的学生网络取得更好的表现。此外，我们的方法允许研究人员从更深的网络中提取知识，以进一步改善学生。我们的代码公开：\ url {https://github.com/wangshaopu/prue}。

知识蒸馏已成功地应用于各种任务。当前的蒸馏算法通常通过模仿教师的产出来改善学生的表现。本文表明，教师还可以通过指导学生的功能恢复来提高学生的代表权。从这个角度来看，我们提出了掩盖的生成蒸馏（MGD），这很简单：我们掩盖了学生功能的随机像素，并强迫它通过简单的块生成教师的完整功能。 MGD是一种真正的基于特征的蒸馏方法，可用于各种任务，包括图像分类，对象检测，语义分割和实例分割。我们在具有广泛数据集的不同模型上进行了实验，结果表明所有学生都取得了出色的改进。值得注意的是，我们将RESNET-18从69.90％提高到71.69％的Imagenet Top-1精度，带有Resnet-50骨架的视网膜从37.4到41.0界盒映射，基于Resnet-50的独奏从33.1到33.1至36.2 Mask Map和DeepLabV3， 18从73.20到76.02 miou。我们的代码可在https://github.com/yzd-v/mgd上找到。

知识蒸馏是通过知识转移模型压缩的有效稳定的方法。传统知识蒸馏（KD）是将来自大型和训练有素的教师网络的知识转移到小型学生网络，这是一种单向过程。最近，已经提出了深度相互学习（DML）来帮助学生网络协同和同时学习。然而，据我们所知，KD和DML从未在统一的框架中共同探索，以解决知识蒸馏问题。在本文中，我们调查教师模型在KD中支持更值得信赖的监督信号，而学生则在DML中捕获教师的类似行为。基于这些观察，我们首先建议将KD与DML联合在统一的框架中。此外，我们提出了一个半球知识蒸馏（SOKD）方法，有效提高了学生和教师的表现。在这种方法中，我们在DML中介绍了同伴教学培训时尚，以缓解学生的模仿困难，并利用KD训练有素的教师提供的监督信号。此外，我们还显示我们的框架可以轻松扩展到基于功能的蒸馏方法。在CiFAR-100和Imagenet数据集上的广泛实验证明了所提出的方法实现了最先进的性能。

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。

作为模型压缩的一种有前途的方法，知识蒸馏通过从繁琐的知识转移知识来改善紧凑模型的性能。用于指导学生培训的知识很重要。语义分割中的先前蒸馏方法努力从这些特征中提取各种形式的知识，涉及依靠先前信息并具有有限的性能提高的精心手动设计。在本文中，我们提出了一种称为标准化功能蒸馏（NFD）的简单而有效的特征蒸馏方法，旨在实现原始功能的有效蒸馏，而无需手动设计新的知识形式。关键的想法是防止学生专注于模仿通过归一化的教师特征响应的幅度。我们的方法可获得有关CityScapes，VOC 2012和ADE20K数据集的语义细分的最新蒸馏结果。代码将可用。

Knowledge distillation (KD) has gained a lot of attention in the field of model compression for edge devices thanks to its effectiveness in compressing large powerful networks into smaller lower-capacity models. Online distillation, in which both the teacher and the student are learning collaboratively, has also gained much interest due to its ability to improve on the performance of the networks involved. The Kullback-Leibler (KL) divergence ensures the proper knowledge transfer between the teacher and student. However, most online KD techniques present some bottlenecks under the network capacity gap. By cooperatively and simultaneously training, the models the KL distance becomes incapable of properly minimizing the teacher's and student's distributions. Alongside accuracy, critical edge device applications are in need of well-calibrated compact networks. Confidence calibration provides a sensible way of getting trustworthy predictions. We propose BD-KD: Balancing of Divergences for online Knowledge Distillation. We show that adaptively balancing between the reverse and forward divergences shifts the focus of the training strategy to the compact student network without limiting the teacher network's learning process. We demonstrate that, by performing this balancing design at the level of the student distillation loss, we improve upon both performance accuracy and calibration of the compact student network. We conducted extensive experiments using a variety of network architectures and show improvements on multiple datasets including CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet. We illustrate the effectiveness of our approach through comprehensive comparisons and ablations with current state-of-the-art online and offline KD techniques.

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the teacher model, and in this sense, only strong teacher models are deployed to teach weaker students in practice. In this work, we challenge this common belief by following experimental observations: 1) beyond the acknowledgment that the teacher can improve the student, the student can also enhance the teacher significantly by reversing the KD procedure; 2) a poorly-trained teacher with much lower accuracy than the student can still improve the latter significantly. To explain these observations, we provide a theoretical analysis of the relationships between KD and label smoothing regularization. We prove that 1) KD is a type of learned label smoothing regularization and 2) label smoothing regularization provides a virtual teacher model for KD. From these results, we argue that the success of KD is not fully due to the similarity information between categories from teachers, but also to the regularization of soft targets, which is equally or even more important.Based on these analyses, we further propose a novel Teacher-free Knowledge Distillation (Tf-KD) framework, where a student model learns from itself or manuallydesigned regularization distribution. The Tf-KD achieves comparable performance with normal KD from a superior teacher, which is well applied when a stronger teacher model is unavailable. Meanwhile, Tf-KD is generic and can be directly deployed for training deep neural networks. Without any extra computation cost, Tf-KD achieves up to 0.65% improvement on ImageNet over well-established baseline models, which is superior to label smoothing regularization.

知识蒸馏（KD）是一个有效的框架，旨在将有意义的信息从大型老师转移到较小的学生。通常，KD通常涉及如何定义和转移知识。以前的KD方法通常着重于挖掘各种形式的知识，例如功能地图和精致信息。但是，知识源自主要监督任务，因此是高度特定于任务的。在自我监督的代表学习的最新成功中，我们提出了一项辅助自我实施的增强任务，以指导网络学习更多有意义的功能。因此，我们可以从KD的这项任务中得出软性自我实施的增强分布作为更丰富的黑暗知识。与以前的知识不同，此分布编码从监督和自我监督的特征学习中编码联合知识。除了知识探索之外，我们建议在各个隐藏层上附加几个辅助分支，以充分利用分层特征图。每个辅助分支都被指导学习自学的增强任务，并将这种分布从教师到学生提炼。总体而言，我们称我们的KD方法为等级自我实施的增强知识蒸馏（HSSAKD）。标准图像分类的实验表明，离线和在线HSSAKD都在KD领域达到了最先进的表现。对象检测的进一步转移实验进一步验证了HSSAKD可以指导网络学习更好的功能。该代码可在https://github.com/winycg/hsakd上找到。

Figure 1. An illustration of standard knowledge distillation. Despite widespread use, an understanding of when the student can learn from the teacher is missing.

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conducted on different tasks show that the proposed method improves educated student models with a significant margin. In particular for metric learning, it allows students to outperform their teachers' performance, achieving the state of the arts on standard benchmark datasets.