Fine-grained Image Classification Based on MogaNet Network and Multi-level Gating Mechanism

Dahai Li¹Su Chen^2*

• ¹Zhengzhou University of Science and Technology, Zhengzhou, China
• ²Henan Vocational College of Water Conservancy and Environment, Zhengzhou, China

Fine-grained image classification tasks are faced with challenges such as difficulty in labeling, scarcity of samples and small category differences. To solve this problem, this paper proposes a novel fine-grained image classification method based on MogaNet network and multi-level gating mechanism. A feature extraction network based on MogaNet is constructed, and multi-scale feature fusion is combined to fully mine image information. The context information extractor is designed to align and filter more discriminative local features using the semantic context of the network, so as to strengthen the ability of the network to capture detailed features. Meanwhile, a multi-level gating mechanism is introduced to obtain the saliency features of images. A feature elimination strategy is proposed to suppress the interference of fuzzy class features and background noise. A loss function is designed to constrain fuzzy class features elimination and classification prediction. Experimental results show that the new method can be used in 5-shot tasks of four public datasets: Mini-ImageNet, CUB-200-2011, Stanford Dogs and Stanford Cars. The accuracy rates reach 79.33%, 87.58%, 79.34% and 83.82% respectively, which show better performance than the other state-of-the-art image classification methods.