Interpretable Attention Guided Network for Fine-Grained Visual Classification
| Autor: | Bo Zhao, Zhenhuan Huang, Xiaoyue Duan, Baochang Zhang, Jinhu Lu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
business.industry
Computer science 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre Object (computer science) 01 natural sciences Discriminative model Bounding overwatch 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Feature (machine learning) 020201 artificial intelligence & image processing Artificial intelligence Representation (mathematics) Focus (optics) business computer 0105 earth and related environmental sciences Interpretability |
| Zdroj: | Pattern Recognition. ICPR International Workshops and Challenges ISBN: 9783030687984 ICPR Workshops (4) |
| Popis: | Fine-grained visual classification (FGVC) is challenging but more critical than traditional classification tasks. It requires distinguishing different subcategories with the inherently subtle intra-class object variations. Previous works focus on enhancing the feature representation ability using multiple granularities and discriminative regions based on the attention strategy or bounding boxes. However, these methods highly rely on deep neural networks which lack interpretability. We propose an Interpretable Attention Guided Network (IAGN) for fine-grained visual classification. The contributions of our method include: i) an attention guided framework which can guide the network to extract discriminitive regions in an interpretable way; ii) a progressive training mechanism obtained to distill knowledge stage by stage to fuse features of various granularities; iii) the first interpretable FGVC method with a competitive performance on several standard FGVC benchmark datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|