Re-rank Coarse Classification With Local Region Enhanced Features For Fine-grained Image Recognition

Abstract

Fine-grained image recognition is very challenging due to the difficulty of capturing both semantic global features and discriminative local features. Meanwhile, these two features are not easy to be integrated, which are even conflicting when used simultaneously. In this paper, a retrieval-based coarse-to-fine framework is proposed, where we re-rank the TopN classification results by using the local region enhanced embedding features to improve the Top1 accuracy (based on the observation that the correct category usually resides in TopN results). To obtain the discriminative regions for distinguishing the fine-grained images, we introduce a weakly-supervised method to train a box generating branch with only image-level labels. In addition, to learn more effective semantic global features, we design a multi-level loss over an automatically constructed hierarchical category structure. Experimental results show that our method achieves state-of-the-art performance on three benchmarks: CU

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2021re

Related papers

• Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval (2023)9.35
• Simultaneous Region Localization And Hash Coding For Fine-grained Image Retrieval (2019)0.00
• Coarse2fine: Two-layer Fusion For Image Retrieval (2016)0.00
• Global-to-local Or Local-to-global? Enhancing Image Retrieval With Efficient Local Search And Effective Global Re-ranking (2025)0.00
• Grafit: Learning Fine-grained Image Representations With Coarse Labels (2020)12.93
• Self-supervising Fine-grained Region Similarities For Large-scale Image Localization (2020)15.85
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
• Instance Retrieval At Fine-grained Level Using Multi-attribute Recognition (2018)0.00