Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation

TL;DR

This paper introduces coalescent projections and latent space reservation techniques to improve cross-domain few-shot learning, effectively handling domain shifts with minimal parameter updates and pseudo-class generation.

Contribution

It proposes coalescent projection as a successor to soft prompts and a pseudo-class generation method to enhance model adaptation to unseen domains.

Findings

Outperforms state-of-the-art methods on BSCD-FSL benchmark

Effective in extreme domain-shift scenarios

Reduces overfitting by limiting parameter updates

Abstract

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}.