Learning Semantically Enhanced Feature for Fine-Grained Image Classification
- 28 August 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 27 (10709908) , 1545-1549
Abstract
We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter. Unlike previous methods that rely on complex part localization modules, our approach learns fine-grained features by enhancing the semantics of sub-features of a global feature. Specifically, we first achieve the sub-feature semantic by arranging feature channels of a CNN into different groups through channel permutation. Meanwhile, to enhance the discriminability of sub-features, the groups are guided to be activated on object parts with strong discriminability by a weighted combination regularization. Our approach is parameter parsimonious and can be easily integrated into the backbone model as a plug-and-play module for end-to-end training with only image-level supervision. Experiments verified the effectiveness of our approach and validated its comparable performance to the state-of-the-art methods. Code is available at https://github.com/cswluo/SEFKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61702197, 61906067)
- NSFGD (2020A151501813, 2017A030310261)
This publication has 15 references indexed in Scilit:
- Learning to Navigate for Fine-Grained Classification2018
- Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition2018
- Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition2018
- Net2Vec: Quantifying and Explaining How Concepts are Encoded by Filters in Deep Neural Networks2018
- Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition2017
- Kernel Pooling for Convolutional Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- 3D Object Representations for Fine-Grained Categorization2013
- ImageNet: A large-scale hierarchical image database2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998