TransIFC : Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

14 Scopus Citations
View graph of relations


  • Hai Liu
  • Cheng Zhang
  • Tingting Liu
  • Zhaoli Zhang


Original languageEnglish
Journal / PublicationIEEE Transactions on Multimedia
Online published20 Jan 2023
Publication statusOnline published - 20 Jan 2023


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) module. The HSFA module aggregates the multiscale information of bird images by concatenating multilayer features. The FFA module extracts the invariant cues of birds through feature selection based on discrimination scores. Transformer is employed as the backbone to reveal the long-dependent semantic relationships in bird images. Moreover, abundant visualizations are provided to prove the interpretability of the HSFA and FFA modules in TransIFC. Comprehensive experiments demonstrate that TransIFC can achieve state-of-the-art performance on the CUB-200-2011 dataset (91.0%) and the NABirds dataset (90.9%). Finally, extended experiments have been conducted on the Stanford Cars dataset to suggest the potential of generalizing our method on other fine-grained visual classification tasks. © 2023 IEEE.

Research Area(s)

  • Birds, Deep learning, Feature extraction, Image classification, Image recognition, Invariant cues, Semantics, Task analysis, Transformer, Transformers