Attribute-Aware Attention Model for Fine-grained Representation Learning

By Kai Han, Jianyuan Guo, Mingjian Zhu. 2018

132 citations recorded by the source corpus.

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 $A^3M$.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yunhe Wang
3. Kai Han
4. Chunjing Xu
5. Jianyuan Guo
6. Qi Tian
7. Luc Van Gool
8. Yi Yang

Citations in the corpus

• GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet (2020, background): “By dint of automatic feature engineering, deep neural networks (DNNs) have achieved remarkable success in various computer vision tasks, such as image classification [37, 36, 41, 33, 32, 15, 39], visual generation [34, 35], image retrieval [40, 7, 8, 12] and semantic comprehension [18, 17].”
• Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets (2020, background): “Deep convolutional neural networks (CNNs) have achieved great success in many visual tasks, such as image recognition [21, 12, 9], object detection [36, 28, 8], and super-resolution [20, 46, 40].”
• Low-resolution Visual Recognition via Deep Feature Distillation (2019, background): “The recent success of deep neural networks has largely boosted the computer vision applications such as visual recognition [1, 2, 3, 4], person re-identification [5], face recognition [6, 7].”
• A Survey on Vision Transformer (2020, methodology): “[43] utilize the attributeaware attention to enhance the representation of CNNs.”
• GhostNet: More Features From Cheap Operations (2019, methodology): “Deep convolutional neural networks have shown excellent performance on various computer vision tasks, such as image recognition [30, 13], object detection [43, 33], and semantic segmentation [4].”
• ABD-Net: Attentive but Diverse Person Re-Identification (2019, unknown): “30 * AM [66] (2018 ACM MM) 86.”