Data-driven Meta-set Based Fine-Grained Visual Classification

Abstract

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method for fine-grained visual recognition. However, label noise in the web training set can severely degrade the model performance. To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition. Specifically, guided by a small amount of clean meta-set, we train a selection net in a meta-learning manner to distinguish in- and out-of-distribution noisy images. To further boost the robustness of model, we also learn a labeling net to correct the labels of in-distribution noisy data. In this way, our proposed method can alleviate the harmful effects caused by out-of-distribution noise and properly exploit the in-distribution noisy samples for training. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to state-of-the-art noise-robust methods.

arXiv commentaccepted by ACM MM 2020

References in corpus (6)

• Fine-Grained Visual Classification of Aircraft
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Object-Part Attention Model for Fine-grained Image Classification
• Weakly Supervised Fine-Grained Image Categorization
• Personalized Age Progression with Bi-level Aging Dictionary Learning