Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation
Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation
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.
Naeem Paeedeh、Mahardhika Pratama、Wolfgang Mayer、Jimmy Cao、Ryszard Kowlczyk
计算技术、计算机技术
Naeem Paeedeh,Mahardhika Pratama,Wolfgang Mayer,Jimmy Cao,Ryszard Kowlczyk.Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation[EB/OL].(2025-07-21)[2025-08-10].https://arxiv.org/abs/2507.15243.点此复制
评论