English
Related papers

Related papers: Turbo Training with Token Dropout

200 papers

Popular video training methods mainly operate on a fixed number of tokens sampled from a predetermined spatiotemporal grid, resulting in sub-optimal accuracy-computation trade-offs due to inherent video redundancy. They also lack…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Chenting Wang , Kunchang Li , Tianxiang Jiang , Xiangyu Zeng , Yi Wang , Limin Wang

Video transformer models require huge amounts of compute resources due to the spatio-temporal scaling of the input. Tackling this, recent methods have proposed to drop or merge tokens for image models, whether randomly or via learned…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Sam Pollard , Michael Wray

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating…

Computer Vision and Pattern Recognition · Computer Science 2024-11-11 Rohan Choudhury , Guanglei Zhu , Sihan Liu , Koichiro Niinuma , Kris M. Kitani , László Jeni

Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by…

Machine Learning · Computer Science 2023-05-05 Bohan Zhuang , Jing Liu , Zizheng Pan , Haoyu He , Yuetian Weng , Chunhua Shen

End-to-end training of multi-agent systems offers significant advantages in improving multi-task performance. However, training such models remains challenging and requires extensive manual design and monitoring. In this work, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Zewei Zhou , Seth Z. Zhao , Tianhui Cai , Zhiyu Huang , Bolei Zhou , Jiaqi Ma

Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Leqi Shen , Tianxiang Hao , Tao He , Sicheng Zhao , Yifeng Zhang , Pengzhang Liu , Yongjun Bao , Guiguang Ding

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Machine Learning · Computer Science 2024-11-06 Hanrui Yan , Dan Shao

Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods mainly pay attention…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Fanhu Zeng , Deli Yu , Zhenglun Kong , Hao Tang

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

Machine Learning · Computer Science 2023-01-25 Muralidhar Andoorveedu , Zhanda Zhu , Bojian Zheng , Gennady Pekhimenko

Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Matthew Dutson , Yin Li , Mohit Gupta

Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token numbers. Existing efforts in efficient training focus on reducing model sizes or…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Dingkun Zhang , Shuhan Qi , Yulin Wu , Xinyu Xiao , Xuan Wang , Long Chen

Contrastive learning has become one of the most impressive approaches for multi-modal representation learning. However, previous multi-modal works mainly focused on cross-modal understanding, ignoring in-modal contrastive learning, which…

Machine Learning · Computer Science 2024-09-17 Zhiyu Zhang , Da Liu , Shengqiang Liu , Anna Wang , Jie Gao , Yali Li

Inspired by the success of transformer-based pre-training methods on natural language tasks and further computer vision tasks, researchers have begun to apply transformer to video processing. This survey aims to give a comprehensive…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Ludan Ruan , Qin Jin

Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Recently, DETR-based models for TAD have been prevailing thanks to their unique benefits. However, transformers demand a huge dataset, and…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Jihwan Kim , Miso Lee , Jae-Pil Heo

Maximum entropy models are considered by many to be one of the most promising avenues of language modeling research. Unfortunately, long training times make maximum entropy research difficult. We present a novel speedup technique: we change…

Computation and Language · Computer Science 2007-05-23 Joshua Goodman

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Shuvam Chakraborty , Burak Uzkent , Kumar Ayush , Kumar Tanmay , Evan Sheehan , Stefano Ermon

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory…

Computer Vision and Pattern Recognition · Computer Science 2021-09-23 Sangho Lee , Youngjae Yu , Gunhee Kim , Thomas Breuel , Jan Kautz , Yale Song

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Seon-Ho Lee , Jue Wang , Zhikang Zhang , David Fan , Xinyu Li
‹ Prev 1 2 3 10 Next ›