cs.AI updates on arXiv.org 07月22日 12:44
Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出了一种新的跨域小样本学习模型Coalescent Projection,通过伪类别生成和自监督转换,有效解决传统方法中参数更新过多导致过拟合的问题,在BSCD-FSL基准测试中表现出色。

arXiv:2507.15243v1 Announce Type: cross Abstract: Despite the progress in Cross-Domain Few-Shot Learning (CD-FSL), a model pre-trained with DINO combined with a prototypical classifier outperforms the latest SOTA methods. A crucial limitation that needs to be overcome is that updating too many parameters of the transformers leads to overfitting due to the scarcity of labeled samples. To address this challenge, we propose a new concept, Coalescent Projection (CP), as an effective successor to soft prompts. Additionally, we propose a novel pseudo-class generation method combined with Self-Supervised Transformations (SSTs) that relies solely on the base domain to prepare the network for encountering unseen samples from different domains. The proposed method exhibits its effectiveness in comprehensive experiments on the extreme domain shift scenario of the BSCD-FSL benchmark. Our code is published at https://github.com/Naeem-Paeedeh/CPLSR.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

CD-FSL Coalescent Projection 跨域学习 小样本学习 BSCD-FSL
相关文章