# Attribute-Aware Attention Model for Fine-grained Representation Learning Source: [Attribute-Aware Attention Model for Fine-grained Representation Learning]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:59:55.808Z Authors: Kai Han, Jianyuan Guo, Chao Zhang, Mingjian Zhu Published: 2019-01-02T14:22:59.000Z ## Abstract How to learn a discriminative fine-grained representation is a key point in many computer vision applications, such as person re-identification, fine-grained classification, fine-grained image retrieval, etc. Most of the previous methods focus on learning metrics or ensemble to derive better global representation, which are usually lack of local information. Based on the considerations above, we propose a novel Attribute-Aware Attention Model ($A^3M$), which can learn local attribute representation and global category representation simultaneously in an end-to-end manner. The proposed model contains two attention models: attribute-guided attention module uses attribute information to help select category features in different regions, at the same time, category-guided attention module selects local features of different attributes with the help of category cues. Through this attribute-category reciprocal process, local and global features benefit from each other. Finally, the resulting feature contains more intrinsic information for image recognition instead of the noisy and irrelevant features. Extensive experiments conducted on Market-1501, CompCars, CUB-200-2011 and CARS196 demonstrate the effectiveness of our $A^3M$. Code is available at https://github.com/iamhankai/attribute-aware-attention. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CompCars (test)](): Image Classification; CompCars (test); Accuracy: 95.4. - [Image Classification on CompCars Web (test)](): Image Classification; CompCars Web (test); Top-1 Acc: 95.4. - [Period Dating on Bronze Ding (test)](): Period Dating; Bronze Ding (test); Overall Accuracy (OA): 75.12. - [Image Classification on CUB-200-2011 (test)](): Image Classification; CUB-200-2011 (test); Top-1 Acc: 86.2. - [Image Retrieval on CUB-200 2011 (test)](): Image Retrieval; CUB-200-2011 (test); Recall@1: 61.2. - [Person Re-identification on Market1501 (test)](): Person Re-Identification; Market1501 (test); Rank-1 Accuracy: 86.54. - [Person Re-identification on Market 1501](): Person Re-Identification; Market 1501; mAP: 69. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()