Journal
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
Volume 14, Issue 4, Pages 1105-1117Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s13042-022-01685-6
Keywords
Fine-grained image recognition; Uncertainty estimation; Information fusion; D-S evidence theory
Categories
Ask authors/readers for more resources
In this paper, we propose an end-to-end trusted multi-granularity information fusion (TMGIF) model for weakly-supervised fine-grained image recognition. By automatically extracting and evaluating the quality of multi-granularity information, and progressively fusing these information, the model is able to generate reliable and interpretable recognition results.
Fine-grained image recognition (FGIR) is more challenging than general image recognition tasks due to the inherently subtle object variation. The existing FGIR methods are mainly based on single-granularity feature fusion, the extracted fused features often cannot fully reflect the characteristics of the object, and the recognition results based on the fused feature also lack interpretability. To solve this problem, we propose a novel end-to-end trusted multi-granularity information fusion (TMGIF) model for weakly-supervised fine-grained image recognition. It can automatically extract multi-granularity information representation for a fine-grained image, further evaluate the quality of information granules, and then progressively fuse multi-granularity information according to the quality to obtain a reliable and interpretable recognition result. We evaluate TMGIF on three standard benchmark datasets, and demonstrate the proposed method can provide competitive results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available