Dataset Bias Prediction for Few-Shot Image Classification

Dataset bias is a significant obstacle that negatively affects image classification performance, especially in few-shot learning, where datasets have limited samples per class. However, few studies have focused on this issue. To address this, we propose a bias prediction network that recovers biases such as color from the extracted features of image data, resulting in performance improvement in few-shot image classification. If the network can easily recover the bias, the extracted features may contain the bias. Therefore, the whole framework is trained to extract features that are difficult for the bias prediction network to recover. We evaluate our method by integrating it with several existing few-shot learning models across multiple benchmark datasets. The results show that the proposed network can improve the performance in different scenarios. The proposed approach effectively reduces the negative effect of the dataset bias, resulting in the performance improvements in few-shot image classification. The proposed bias prediction model is easily compatible with other few-shot learning models, and applicable to various real-world applications where biased samples are prevalent, such as VR/AR systems and computer vision applications.

Automated summary

Dataset bias is a significant obstacle in image classification, particularly in few-shot learning with limited samples per class. To address this, we propose a bias prediction network that recovers biases from image data features, improving few-shot image classification performance. Our method trains the framework to extract features that are difficult for the bias prediction network to recover. We evaluate our approach on multiple benchmark datasets and integrate it with existing few-shot learning models, showing improved performance in different scenarios. The proposed bias prediction model is compatible with other few-shot learning models and applicable to real-world applications with biased samples.