Papers › Structural feature enhanced transformer for fine-grained image recognition

Structural feature enhanced transformer for fine-grained image recognition

14 Jun 2025Pattern Recognition 2025 6archive 2025-07-28

Ying Yu, Wei Wei, Cairong Zhao, Jin Qian, Enhong Chen

Existing fine-grained image recognition (FGIR) models mainly rely on high-level semantic features to extract discriminative information, ignoring the potential role of the overall structural information of objects and the structural relationships between key parts. To address this issue, we propose the Structural Feature Enhancement Transformer (SFETrans). SFETrans consists of a visual transformer backbone network responsible for extracting complex semantic features. Additionally, it includes a structural modeling (SM) branch and an amplitude component exchange (ACE) module, both dedicated to enhancing the learning of structural features. The SM branch actively models the structural relationships between key parts of objects and extracts corresponding structural features, while the ACE module guides the model to learn structural information in the phase spectrum by introducing implicit constraints during training. By synergizing the backbone network and the two modules, SFETrans exhibits competitive performance on four benchmark datasets and outperforms other comparison methods in terms of computational efficiency.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyFine-Grained Image ClassificationFine-Grained Image Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification CUB-200-2011 SFETrans Accuracy 91.8 #6 of 30 Archive leaderboard report
Fine-Grained Image Classification NABirds SFETrans Accuracy 91.1 #12 of 30 Archive leaderboard report
Fine-Grained Image Classification Stanford Dogs SFETrans Accuracy 92.4 #10 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections