Ta-Adapter: Enhancing few-shot CLIP with task-aware encoders-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Ta-Adapter: Enhancing few-shot CLIP with task-aware encoders

Published:2024-09 Issue: Volume:153 Page:110559
ISSN:0031-3203
Container-title:Pattern Recognition
language:en
Short-container-title:Pattern Recognition

Author:

Zhang Wenbo^ORCID,Zhang Yifan^ORCID,Deng Yuyang,Zhang Wenlong^ORCID,Lin Jianfeng,Huang Binqiang,Zhang Jinlu,Yu Wenhao

Funder

National Natural Science Foundation of China

Publisher

Elsevier BV

Reference66 articles.

1. Uniclip: Unified framework for contrastive language-image pre-training;Lee;Adv. Neural Inf. Process. Syst.,2022

2. Learning visual representation from modality-shared contrastive language-image pre-training;You,2022

3. Learning transferable visual models from natural language supervision;Radford,2021

4. Representation learning with contrastive predictive coding;Oord,2018

5. An image is worth 16x16 words: Transformers for image recognition at scale;Dosovitskiy,2020

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Visual primitives as words: Alignment and interaction for compositional zero-shot learning;Pattern Recognition;2025-01

2. BB-GeoGPT: A framework for learning a large language model for geographic information science;Information Processing & Management;2024-09

3. GeoGPT: An assistant for understanding and processing geospatial tasks;International Journal of Applied Earth Observation and Geoinformation;2024-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP