Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
This work addresses the problem of overfitting in FGVC for computer vision researchers, offering an incremental improvement over existing pre-training methods.
The paper tackles the challenge of fine-grained visual categorization (FGVC) by proposing MetaFGNet, a model trained with a regularized meta-learning objective to optimize parameters for target task adaptation, and includes a sample selection scheme for auxiliary data, showing efficacy on benchmark datasets.
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing methods usually adopt a strategy of pre-training the models using a rich set of auxiliary data, followed by fine-tuning on the target FGVC task. However, the objective of pre-training does not take the target task into account, and consequently such obtained models are suboptimal for fine-tuning. To address this issue, we propose in this paper a new deep FGVC model termed MetaFGNet. Training of MetaFGNet is based on a novel regularized meta-learning objective, which aims to guide the learning of network parameters so that they are optimal for adapting to the target FGVC task. Based on MetaFGNet, we also propose a simple yet effective scheme for selecting more useful samples from the auxiliary data. Experiments on benchmark FGVC datasets show the efficacy of our proposed method.