TransIFC: Invariant Cues-Aware Feature Concentration Learning for Efficient Fine-Grained Bird Image Classification
Central China Normal University · Beijing University of Technology · +3 more institutions
Abstract
Fine-grained bird image classification (FBIC) is not only meaningful for endangered bird observation and protection but also a prevalent task for image classification in multimedia processing and computer vision. However, FBIC suffers from several challenges, such as bird molting, complex background, and arbitrary bird posture. To effectively tackle these challenges, we present a novel invariant cues-aware feature concentration Transformer (TransIFC), which learns invariant and core information in bird images. To this end, two novel modules are proposed to leverage the characteristics of bird images, namely, the hierarchy stage feature aggregation (HSFA) module and the feature in feature abstraction (FFA)…
Citation impact
- FWCI
- 49.91
- Percentile
- 100%
- References
- 50
Authors
6- HLHai LiuCorresponding
Central China Normal University
- CZCheng Zhang
Central China Normal University
- YDYongjian Deng
Beijing University of Technology
- BXBochen Xie
City University of Hong Kong, City University of Hong Kong, Shenzhen Research Institute
- TLTingting Liu
City University of Hong Kong, Hubei University
Topics & keywords
- Computer science
- Artificial intelligence
- Pattern recognition (psychology)
- Invariant (physics)
- Interpretability
- Leverage (statistics)
- Feature extraction
Funding
- NNNational Natural Science Foundation of ChinaAwards: 6247077114, 62177019, 62005092, 62177018, 62173286, 62211530433, 62277041, 62077020, 92167102, 62377037, 62203024
- NSNatural Science Foundation of Jiangxi ProvinceAwards: 20232BAB212026, 20242BAB2S107
- FRFundamental Research Funds for the Central UniversitiesAwards: CCNU20ZT017, CCNU2020ZN008