为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速览选取了来自电子科技大学的小样本学习 (Few-shot learning)的工作。该工作由宋井宽老师指导,论文一作罗旭同学录制。 论文题目:A Closer Look at Few-shot Classification Again 作者列表: 罗旭 (电子科技大学)、吴昊 (电子科技大学)、张继 (电子科技大学)、高联丽 (电子科技大学)、徐菁 (哈尔滨工业大学深圳校区)、宋井宽 (电子科技大学) B站观看网址: 论文摘要: Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions. 论文信息: [1] Xu Luo, Hao Wu, Ji Zhang, Lianli Gao, Jing Xu, Jingkuan Song, “A Closer Look at Few-shot Classification Again,” ICML 2023. 论文链接: [http://proceedings.mlr.press/v202/luo23e/luo23e.pdf ] 代码链接: [https://github.com/Frankluox/CloserLookAgainFewShot] 视频讲者简介: 罗旭,电子科技大学计算机学院博士生。研究兴趣目前集中于对大模型的小样本迁移能力 (比如finetune和in-context learning)的分析与理解。以一作身份于NeurIPS/ ICML发表论文3篇,担任NeurIPS/ ICML/ ICLR/ CVPR/ ICCV/ ECCV/ TPAMI/ TIP等会议期刊审稿人。 个人主页: https://frankluox.github.io/ 特别鸣谢本次论文速览主要组织者: 月度轮值AC:张磊 (重庆大学)、谢雨彤 (阿德莱德大学) 活动参与方式 1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们! 直播地址: https://live.bilibili.com/22300737; 历史视频观看地址: https://space.bilibili.com/562085182/ 2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ S群,群号:317920537); *注:申请加入VALSE QQ群时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。 3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。 4、您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。 |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2024-11-21 21:50 , Processed in 0.012711 second(s), 14 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.