[TIP 2022] TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient FGVC

Contents

• Introduction
• Proposed TransIFC Model
• • Feature map generation
  • FFA module
  • HSFA module
  • Classification head
  • MAP-based model
• Experiments
• References

Introduction

• Challenges of Fine-grained Bird Image Classification. (1) Bird molting: Some birds undergo an annual molt (change their feather) as season changes (Figs. 1(a) and 1(b)). (2) Complex background. (3) Arbitrary posture