Transformers are successfully applied to computer vision due to their
powerful modeling capacity with self-attention. However, the excellent
performance of transformers heavily depends on enormous training images. Thus,
a data-efficient transformer solution is urgently needed. In this work, we
propose an early knowledge distillation framework, which is termed as DearKD,
to improve the data efficiency required by transformers. Our DearKD is a
two-stage framework that first distills the inductive biases from the early
intermediate layers of a CNN and then gives the transformer full play by
training without distillation. Further, our DearKD can be readily applied to
the extreme data-free case where no real images are available. In this case, we
propose a boundary-preserving intra-divergence loss based on DeepInversion to
further close the performance gap against the full-data counterpart. Extensive
experiments on ImageNet, partial ImageNet, data-free setting and other
downstream tasks prove the superiority of DearKD over its baselines and
state-of-the-art methods.

本文提出了一种早期知识蒸馏框架 (DearKD)，通过从卷积神经网络的早期中间层中提取归纳偏差然后通过无蒸馏进行训练，以提高变压器所需的数据效率。我们还针对极端的零数据情况提出了一种基于 DeepInversion 的边界保留内部分歧损失，从而进一步缩小与完整数据对照组之间的性能差距。针对 ImageNet、partial ImageNet、无数据设置和其他下游任务的大量实验证明 DearKD 优于其基准和最先进的方法。

DearKD：用于 Vision Transformers 的数据高效早期知识蒸馏

DearKD: Data-Efficient Early Knowledge Distillation for Vision  Transformers

We introduce DeepInversion, a new method for synthesizing images from the
image distribution used to train a deep neural network. We 'invert' a trained
network (teacher) to synthesize class-conditional input images starting from
random noise, without using any additional information about the training
dataset. Keeping the teacher fixed, our method optimizes the input while
regularizing the distribution of intermediate feature maps using information
stored in the batch normalization layers of the teacher. Further, we improve
the diversity of synthesized images using Adaptive DeepInversion, which
maximizes the Jensen-Shannon divergence between the teacher and student network
logits. The resulting synthesized images from networks trained on the CIFAR-10
and ImageNet datasets demonstrate high fidelity and degree of realism, and help
enable a new breed of data-free applications - ones that do not require any
real images or labeled data. We demonstrate the applicability of our proposed
method to three tasks of immense practical importance -- (i) data-free network
pruning, (ii) data-free knowledge transfer, and (iii) data-free continual
learning. Code is available at this https URL

本文介绍了 DeepInversion 方法用于从神经网络中的图像分布合成图像，使用 Adaptive DeepInversion 提高了生成图像的多样性，并应用于三个数据无关任务中，实现了数据无关的网络剪枝、知识迁移和不断学习。