Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917087686950912 |
|---|---|
| author | Paeedeh, Naeem Pratama, Mahardhika Kamal, Imam Mustafa Mayer, Wolfgang Cao, Jimmy Kowlczyk, Ryszard |
| author_facet | Paeedeh, Naeem Pratama, Mahardhika Kamal, Imam Mustafa Mayer, Wolfgang Cao, Jimmy Kowlczyk, Ryszard |
| contents | 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}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15243 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation Paeedeh, Naeem Pratama, Mahardhika Kamal, Imam Mustafa Mayer, Wolfgang Cao, Jimmy Kowlczyk, Ryszard Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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}. |
| title | Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.15243 |