这项工作介绍了一个新颖的知识蒸馏框架，用于分类任务，其中可用并考虑到现有子类信息。在具有少数类或二进制检测的分类任务（两个类）中，从教师到学生网络传递的信息量受到限制，从而限制了知识蒸馏的效用。可以通过利用有关分类任务中可用类中可能子类的信息来提高性能。为此，我们提出了所谓的子类知识蒸馏（SKD）框架，这是将子类的预测知识从大型教师模型转移到较小的学生的过程。通过SKD，其他有意义的信息不在教师的课堂逻辑中，而是在子类中存在（例如，课堂内的相似之处）将被传达给学生并提高其表现。从数学上讲，我们测量老师可以通过SKD框架为学生提供多少额外信息。开发的框架是在临床应用中评估的，即结直肠息肉分类。在此应用程序中，临床医生提供的注释用于根据注释标签的学习方式来定义子类。接受拟议框架培训的轻巧，低复杂性学生的F1得分为85.05％，比在没有常规知识蒸馏的情况下训练的学生分别提高了2.14％和1.49％的增长。这些结果表明，额外的子类知识（即我们实验中的培训样本0.4656标签位）可以提供有关教师概括的更多信息，因此SKD可以从使用更多信息中受益于提高学生的表现。

这项工作介绍了一个新颖的知识蒸馏框架，用于分类任务，其中可用并考虑到现有子类信息。在具有少量类或二进制检测的分类任务中，从教师到学生的信息量受到限制，从而限制了知识蒸馏的效用。通过利用类中可能的子类信息可以提高性能。为此，我们提出了所谓的子类知识蒸馏（SKD），这是将预测子类知识从老师转移到较小学生的过程。在老师的课堂逻辑中不存在的有意义的信息，而是在子类徽标中存在（例如，课堂内的相似之处）将通过SKD传达给学生，然后将提高学生的表现。从分析上，我们衡量教师可以通过SKD向学生提供多少额外信息，以证明我们工作的功效。开发的框架是在临床应用中评估的，即结直肠息肉分类。这是两个类别和每个类的许多子类的实际问题。在此应用程序中，使用临床医生提供的注释来根据注释标签的学习方式来定义子类。接受SKD框架训练的轻巧，低复杂的学生的F1得分为85.05％，提高了1.47％，比学生分别接受和没有常规知识蒸馏的学生获得了2.10％的收益。接受和没有SKD的学生之间的2.10％的F1得分差距可以通过额外的子类知识来解释，即，每个样本的额外的0.4656标签位可以在我们的实验中转移。

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.

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher. However, applying KD in image regression with a scalar response variable has been rarely studied, and there exists no KD method applicable to both classification and regression tasks yet. Moreover, existing KD methods often require a practitioner to carefully select or adjust the teacher and student architectures, making these methods less flexible in practice. To address the above problems in a unified way, we propose a comprehensive KD framework based on cGANs, termed cGAN-KD. Fundamentally different from existing KD methods, cGAN-KD distills and transfers knowledge from a teacher model to a student model via cGAN-generated samples. This novel mechanism makes cGAN-KD suitable for both classification and regression tasks, compatible with other KD methods, and insensitive to the teacher and student architectures. An error bound for a student model trained in the cGAN-KD framework is derived in this work, providing a theory for why cGAN-KD is effective as well as guiding the practical implementation of cGAN-KD. Extensive experiments on CIFAR-100 and ImageNet-100 show that we can combine state of the art KD methods with the cGAN-KD framework to yield a new state of the art. Moreover, experiments on Steering Angle and UTKFace demonstrate the effectiveness of cGAN-KD in image regression tasks, where existing KD methods are inapplicable.

机器学习中的知识蒸馏是将知识从名为教师的大型模型转移到一个名为“学生”的较小模型的过程。知识蒸馏是将大型网络（教师）压缩到较小网络（学生）的技术之一，该网络可以部署在手机等小型设备中。当教师和学生之间的网络规模差距增加时，学生网络的表现就会下降。为了解决这个问题，在教师模型和名为助教模型的学生模型之间采用了中间模型，这反过来弥补了教师与学生之间的差距。在这项研究中，我们已经表明，使用多个助教模型，可以进一步改进学生模型（较小的模型）。我们使用加权集合学习将这些多个助教模型组合在一起，我们使用了差异评估优化算法来生成权重值。

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teacher) pre-trained network is used to train a smaller (student) network. However, in this paper, we show that the student network performance degrades when the gap between student and teacher is large. Given a fixed student network, one cannot employ an arbitrarily large teacher, or in other words, a teacher can effectively transfer its knowledge to students up to a certain size, not smaller. To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher. Moreover, we study the effect of teacher assistant size and extend the framework to multi-step distillation. Theoretical analysis and extensive experiments on CIFAR-10,100 and ImageNet datasets and on CNN and ResNet architectures substantiate the effectiveness of our proposed approach.

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

基于蒸馏的压缩网络的性能受蒸馏质量的管辖。大型网络（教师）到较小网络（学生）的次优蒸馏的原因主要归因于给定教师与学生对的学习能力中的差距。虽然很难蒸馏所有教师的知识，但可以在很大程度上控制蒸馏质量以实现更好的性能。我们的实验表明，蒸馏品质主要受教师响应的质量来限制，这反过来又受到其反应中存在相似信息的影响。训练有素的大容量老师在学习细粒度辨别性质的过程中丢失了类别之间的相似性信息。没有相似性信息导致蒸馏过程从一个例子 - 许多阶级学习减少到一个示例 - 一类学习，从而限制了教师的不同知识的流程。由于隐式假设只能蒸馏出灌输所知，而不是仅关注知识蒸馏过程，我们仔细审查了知识序列过程。我们认为，对于给定的教师 - 学生对，通过在训练老师的同时找到批量大小和时代数量之间的甜蜜点，可以提高蒸馏品。我们讨论了找到这种甜蜜点以便更好地蒸馏的步骤。我们还提出了蒸馏假设，以区分知识蒸馏和正则化效果之间的蒸馏过程的行为。我们在三个不同的数据集中进行我们的所有实验。

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.

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。

知识蒸馏是将“知识”从大型模型（教师）转移到更紧凑的（学生）的过程，通常在模型压缩的背景下使用。当两个模型都具有相同的体系结构时，此过程称为自distillation。几项轶事表明，一个自灭的学生可以在持有的数据上胜过老师的表现。在这项工作中，我们系统地研究了许多设置。我们首先表明，即使有一个高度准确的老师，自我介绍也使学生在所有情况下都可以超越老师。其次，我们重新审视了（自我）蒸馏的现有理论解释，并确定矛盾的例子，揭示了这些解释的可能缺点。最后，我们通过损失景观几何形状的镜头为自我鉴定的动态提供了另一种解释。我们进行了广泛的实验，以表明自我验证会导致最小化的最小值，从而导致更好的概括。

自我介绍在训练过程中利用自身的非均匀软监管，并在没有任何运行时成本的情况下提高性能。但是，在训练过程中的开销经常被忽略，但是在巨型模型的时代，培训期间的时间和记忆开销越来越重要。本文提出了一种名为ZIPF标签平滑（ZIPF的LS）的有效自我验证方法，该方法使用网络的直立预测来生成软监管，该软监管在不使用任何对比样本或辅助参数的情况下符合ZIPF分布。我们的想法来自经验观察，即当对网络进行适当训练时，在按样品的大小和平均分类后，应遵循分布的分布，让人联想到ZIPF的自然语言频率统计信息，这是在按样品中的大小和平均值进行排序之后进行的。 。通过在样本级别和整个培训期内强制执行此属性，我们发现预测准确性可以大大提高。使用INAT21细粒分类数据集上的RESNET50，与香草基线相比，我们的技术获得了 +3.61％的准确性增长，而与先前的标签平滑或自我验证策略相比，增益增加了0.88％。该实现可在https://github.com/megvii-research/zipfls上公开获得。

知识蒸馏在模型压缩方面取得了显着的成就。但是，大多数现有方法需要原始的培训数据，而实践中的实际数据通常是不可用的，因为隐私，安全性和传输限制。为了解决这个问题，我们提出了一种有条件的生成数据无数据知识蒸馏（CGDD）框架，用于培训有效的便携式网络，而无需任何实际数据。在此框架中，除了使用教师模型中提取的知识外，我们将预设标签作为额外的辅助信息介绍以培训发电机。然后，训练有素的发生器可以根据需要产生指定类别的有意义的培训样本。为了促进蒸馏过程，除了使用常规蒸馏损失，我们将预设标签视为地面真理标签，以便学生网络直接由合成训练样本类别监督。此外，我们强制学生网络模仿教师模型的注意图，进一步提高了其性能。为了验证我们方法的优越性，我们设计一个新的评估度量称为相对准确性，可以直接比较不同蒸馏方法的有效性。培训的便携式网络通过提出的数据无数据蒸馏方法获得了99.63％，99.07％和99.84％的CIFAR10，CIFAR100和CALTECH101的相对准确性。实验结果表明了所提出的方法的优越性。

在多种方式知识蒸馏研究的背景下，现有方法主要集中在唯一的学习教师最终产出问题。因此，教师网络与学生网络之间存在深处。有必要强制学生网络来学习教师网络的模态关系信息。为了有效利用从教师转移到学生的知识，采用了一种新的模型关系蒸馏范式，通过建模不同的模态之间的关系信息，即学习教师模级克矩阵。

Learning style refers to a type of training mechanism adopted by an individual to gain new knowledge. As suggested by the VARK model, humans have different learning preferences like visual, auditory, etc., for acquiring and effectively processing information. Inspired by this concept, our work explores the idea of mixed information sharing with model compression in the context of Knowledge Distillation (KD) and Mutual Learning (ML). Unlike conventional techniques that share the same type of knowledge with all networks, we propose to train individual networks with different forms of information to enhance the learning process. We formulate a combined KD and ML framework with one teacher and two student networks that share or exchange information in the form of predictions and feature maps. Our comprehensive experiments with benchmark classification and segmentation datasets demonstrate that with 15% compression, the ensemble performance of networks trained with diverse forms of knowledge outperforms the conventional techniques both quantitatively and qualitatively.

Knowledge distillation is a widely applicable techniquefor training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a compact student; in privileged learning, a teacher trained with privileged data is distilled to train a student without access to that data. The distillation loss determines how a teacher's knowledge is captured and transferred to the student. In this paper, we propose a new form of knowledge distillation loss that is inspired by the observation that semantically similar inputs tend to elicit similar activation patterns in a trained network. Similarity-preserving knowledge distillation guides the training of a student network such that input pairs that produce similar (dissimilar) activations in the teacher network produce similar (dissimilar) activations in the student network. In contrast to previous distillation methods, the student is not required to mimic the representation space of the teacher, but rather to preserve the pairwise similarities in its own representation space. Experiments on three public datasets demonstrate the potential of our approach.

AI-powered Medical Imaging has recently achieved enormous attention due to its ability to provide fast-paced healthcare diagnoses. However, it usually suffers from a lack of high-quality datasets due to high annotation cost, inter-observer variability, human annotator error, and errors in computer-generated labels. Deep learning models trained on noisy labelled datasets are sensitive to the noise type and lead to less generalization on the unseen samples. To address this challenge, we propose a Robust Stochastic Knowledge Distillation (RoS-KD) framework which mimics the notion of learning a topic from multiple sources to ensure deterrence in learning noisy information. More specifically, RoS-KD learns a smooth, well-informed, and robust student manifold by distilling knowledge from multiple teachers trained on overlapping subsets of training data. Our extensive experiments on popular medical imaging classification tasks (cardiopulmonary disease and lesion classification) using real-world datasets, show the performance benefit of RoS-KD, its ability to distill knowledge from many popular large networks (ResNet-50, DenseNet-121, MobileNet-V2) in a comparatively small network, and its robustness to adversarial attacks (PGD, FSGM). More specifically, RoS-KD achieves >2% and >4% improvement on F1-score for lesion classification and cardiopulmonary disease classification tasks, respectively, when the underlying student is ResNet-18 against recent competitive knowledge distillation baseline. Additionally, on cardiopulmonary disease classification task, RoS-KD outperforms most of the SOTA baselines by ~1% gain in AUC score.

除了使用硬标签的标准监督学习外，通常在许多监督学习设置中使用辅助损失来改善模型的概括。例如，知识蒸馏增加了第二个教师模仿模型训练的损失，在该培训中，教师可能是一个验证的模型，可以输出比标签更丰富的分布。同样，在标记数据有限的设置中，弱标记信息以标签函数的形式使用。此处引入辅助损失来对抗标签函数，这些功能可能是基于嘈杂的规则的真实标签近似值。我们解决了学习以原则性方式结合这些损失的问题。我们介绍AMAL，该AMAL使用元学习在验证度量上学习实例特定的权重，以实现损失的最佳混合。在许多知识蒸馏和规则降解域中进行的实验表明，Amal在这些领域中对竞争基准的增长可显着。我们通过经验分析我们的方法，并分享有关其提供性能提升的机制的见解。

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.

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}。