paper-with-me

Papers

Multitask Vision-Language Prompt Tuning

2022-11-21 · Sheng Shen, Shijia Yang, Tianjun Zhang, Bohan Zhai, Joseph E. Gonzalez, Kurt Keutzer, Trevor Darrell

Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning. We benchmark the proposed MVLPT using three representative prompt tuning methods, namely text prompt tuning, visual prompt tuning, and the unified vision-language prompt tuning. Results in 20 vision tasks demonstrate that the proposed approach outperforms all single-task baseline prompt tuning methods, setting the new state-of-the-art on the few-shot ELEVATER benchmarks and cross-task generalization benchmarks. To understand where the cross-task knowledge is most effective, we also conduct a large-scale study on task transferability with 20 vision tasks in 400 combinations for each prompt tuning method. It shows that the most performant MVLPT for each prompt tuning method prefers different task combinations and many tasks can benefit each other, depending on their visual similarity and label similarity. Code is available at https://github.com/sIncerass/MVLPT.

📄 PDF Abstract BibTeX arXiv:2211.11720

Code (1)

sincerass/mvlpt 공식 구현 pytorch

Tasks

Visual Prompt Tuning

Similar Papers 제목 키워드 기반

SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning

2022-12-21 · M Saiful Bari, Aston Zhang, Shuai Zheng, Xingjian Shi 외

Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potenti…

Language ModelingLanguage Modellingparameter-efficient fine-tuningZero-shot Generalization

Few-shot Multimodal Multitask Multilingual Learning

2023-02-19 · Aman Chadha, Vinija Jain

While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models. Furthermo…

Few-Shot LearningIn-Context LearningNatural Language UnderstandingNER+9

Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning

2023-03-06 · Zhen Wang, Rameswar Panda, Leonid Karlinsky, Rogerio Feris 외

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstrea…

Transfer Learning

Dynamic Prompting: A Unified Framework for Prompt Tuning

2023-03-06 · Xianjun Yang, Wei Cheng, Xujiang Zhao, Wenchao Yu 외

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, …

Position

Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks

2023-07-13 · Denis Coquenet, Clément Rambour, Emanuele Dalsasso, Nicolas Thome

Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, …

Attribute