Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservation
This addresses cross-domain few-shot learning for AI systems needing adaptation to new domains with minimal data, representing an incremental improvement over existing methods.
The paper tackles the problem of overfitting in cross-domain few-shot learning when updating transformer parameters with scarce labeled samples, proposing coalescent projections and pseudo-class generation to achieve state-of-the-art performance on the BSCD-FSL benchmark.
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}.