Journal
KNOWLEDGE-BASED SYSTEMS
Volume 273, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2023.110599
Keywords
Fine-grained recognition; Category similarity; Multi-granularity classification
Categories
Ask authors/readers for more resources
The core of fine-grained recognition is to distinguish subcategories within a broad category based on subtle differences in images. Two important factors that are less explored are the similarity between categories and the different definitions of fine-grained categories. This paper proposes a multi-granularity classification framework that uses label hierarchies, decoupled and re-coupled features, and a joint probability-based loss to achieve state-of-the-art performance in fine-grained recognition.
The core of fine-grained recognition is to distinguish different subcategories within a same broad category through subtle differences in images. Yet two important factors are less explored: Firstly, the degree of similarity between categories, with the more similar categories being more likely to be confused. Secondly, different fine-grained definitions under divergent levels of expertise, with one coarse label corresponding to multiple similar fine categories (e.g., a brand of car has multiple models). In this paper, we discover that multi-granularity label can function as an intermediary for turning inter-category similarity relations into fine-grained recognition performance. Specifically, we first explore the association between label hierarchies in multi-granularity prediction: both coarse and fine label predictions require coarse information, but fine label prediction additionally requires subtle information. Then, a multi-granularity classification framework is proposed, where the extracted feature is decoupled and re-coupled into groups for predicting labels at different granularities, respectively. The key is to involve coarse-grained features in the prediction of finer-level labels. The realization way is to train these features with a joint probability-based loss that we design to reduce inter-task interference through inter-granularity probability relations. Lastly, for tasks without coarse labels, a category similarity matrix is suggested for measuring inter-class similarity and a further non-parametric aggregation method is devised for clustering fine labels into coarse labels. The evaluation is carried out on several fine-grained classification benchmark datasets. Results show that the proposed approach achieves state-of-the-art in multi-granularity classification and exhibits the potential to enhance existing fine-grained recognition models.(c) 2023 Elsevier B.V. All rights reserved.
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