通过递归耦合窄模型，用更少算力训练出高效视觉模型。
Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
- 递归块对角耦合窄模型，无需参数即可构建宽模型
- 相同精度下减少30%计算量，优于从头训练
- 适合资源受限场景，也适合作为下游任务骨干
从零训练高容量视觉模型需要大量计算资源。现有增长方法通常依赖已有窄模型，掩盖了全流程的真实开销。本文提出高效训练协议RBDC，通过参数无增的递归块对角方式耦合独立训练的窄模型，构建宽模型。该方法可灵活分配各阶段训练预算。在ImageNet上基于DeiT和ResNet的实验表明，与标准从头训练相比，RBDC在相近测试准确率下实现30%的FLOPs降低；在相同训练FLOPs下，性能优于模型增长类方法。此外，所提模型作为下游目标检测与实例分割任务的主干网络，表现优于原始模型。
原文摘要 · Abstract (English)
Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often assume the availability of narrower models, obscuring the true computational cost of the entire pipeline. We propose an efficient training protocol, RBDC, that builds wide models by coupling in a parameter-free block-diagonal way narrower, independently trained models in a recursive way. This allows a flexible allocation of the training budget available across all the models involved. Evaluated with vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, our RBDC training protocol shows a much better efficiency than models trained from scratch with the standard protocol, yielding 30% FLOPs reduction at similar test accuracies. It also achieves higher performances at same training FLOPs than training protocols from the model growth literature. Finally, we show that our models can serve as better backbones than their original counterparts for downstream object detection and instance segmentation tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。