Training data-efficient image transformers & distillation through attention
Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer 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 evaluation) 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.
Code (40)
Tasks
Document Image ClassificationDocument Layout AnalysisEfficient ViTsFine-Grained Image Classificationimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
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, …
Knowledge DistillationCo-advise: Cross Inductive Bias Distillation
Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. However, its supremacy degenerates given an in…
Inductive BiasSupervised Masked Knowledge Distillation for Few-Shot Transformers
Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings o…
Few-Shot LearningInductive BiasKnowledge DistillationPluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers
Diffusion Transformers (DiTs) have shown exceptional performance in image generation, yet their large parameter counts incur high computational costs, impeding deployment in resource-constrained settings. To address this…
Image GenerationCOMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers
We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal actio…
Action DetectionAction SpottingKnowledge DistillationSelf-Supervised Learning