# Improving Cross-domain Few-shot Classification with Multilayer Perceptron Source: [Improving Cross-domain Few-shot Classification with Multilayer Perceptron]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:58:23.698Z Authors: Shuanghao Bai, Wanqi Zhou, Zhirong Luan, Donglin Wang, Badong Chen Published: 2023-12-15T07:54:46.000Z ## Abstract Cross-domain few-shot classification (CDFSC) is a challenging and tough task due to the significant distribution discrepancies across different domains. To address this challenge, many approaches aim to learn transferable representations. Multilayer perceptron (MLP) has shown its capability to learn transferable representations in various downstream tasks, such as unsupervised image classification and supervised concept generalization. However, its potential in the few-shot settings has yet to be comprehensively explored. In this study, we investigate the potential of MLP to assist in addressing the challenges of CDFSC. Specifically, we introduce three distinct frameworks incorporating MLP in accordance with three types of few-shot classification methods to verify the effectiveness of MLP. We reveal that MLP can significantly enhance discriminative capabilities and alleviate distribution shifts, which can be supported by our expensive experiments involving 10 baseline models and 12 benchmark datasets. Furthermore, our method even compares favorably against other state-of-the-art CDFSC algorithms. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Cross-domain few-shot classification on CD-FSL (test)](): Cross-domain few-shot classification; CD-FSL (test); ChestX: 0.26. - [Image Classification on CropD (test)](): Image Classification; CropD (test); Accuracy: 58.1. - [Image Classification on Euro (test)](): Image Classification; Euro (test); Accuracy: 75.73. - [Image Classification on ChessX (test)](): Image Classification; ChessX (test); Accuracy: 25.19. - [Classification on ISIC (test)](): Classification; ISIC (test); Top-1 Accuracy: 39.19. - [Image Classification on Flower (test)](): Image Classification; Flower (test); Accuracy: 66.45. ## Original sources and implementation [Original paper]() [PDF]()