Turbo Training with Token Dropout
원문 초록
The objective of this paper is an efficient training method for video tasks. We make three contributions: (1) We propose Turbo training, a simple and versatile training paradigm for Transformers on multiple video tasks. (2) We illustrate the advantages of Turbo training on action classification, video-language representation learning, and long-video activity classification, showing that Turbo training can largely maintain competitive performance while achieving almost 4X speed-up and significantly less memory consumption. (3) Turbo training enables long-schedule video-language training and end-to-end long-video training, delivering competitive or superior performance than previous works, which were infeasible to train under limited resources.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Disentangled representations of microscopy images
Large-Scale Few-Shot Classification with Semi-supervised Hierarchical k-Probabilistic PCAs
Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning
Class incremental learning for video action classification
Support Vector Machines with Time Series Distance Kernels for Action Classification
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.