用融合投影与隐空间保留，提升跨域少样本学习泛化能力
Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation
- 提出共融投影替代软提示，减少参数更新量
- 在BSCD-FSL上实现新最优，跨域迁移性能显著提升
- 适合数据稀缺场景的模型轻量化设计
尽管跨域少样本学习取得进展，但使用DINO预训练结合原型分类器的方法仍优于最新SOTA。其核心挑战在于：过多更新Transformer参数易因标签样本不足导致过拟合。为此，本文提出共融投影（coalescent projection），作为软提示的有效替代方案；同时设计一种仅依赖基础域的伪类别生成方法，结合自监督变换，使网络提前适应未知域样本。在极端域偏移的BSCD-FSL基准测试中，所提方法展现出卓越性能。代码已开源。
原文摘要 · Abstract (English)
Despite the progress in cross-domain few-shot learning, 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, as an effective successor to soft prompts. Additionally, we propose a novel pseudo-class generation method, combined with self-supervised transformations, that relies solely on the base domain to prepare the network to encounter unseen samples from different domains. The proposed method exhibits its effectiveness in comprehensive experiments on the extreme domain-shift problem of the BSCD-FSL benchmark. Our code is published at \href{https://github.com/Naeem-Paeedeh/CPLSR}{https://github.com/Naeem-Paeedeh/CPLSR}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。