现存的细粒度车辆识别器在多个数据集上取得了良好的性能。但这些方法通常运行效率低；而且当图像中存在多辆车时，易受背景干扰，不能准确地定位注意力区域。提出一种快速且准确的车辆识别器FACR，与现存方法相比有如下3个特点：1)其注意力区域定位组件，对图像中背景车辆有很高的鲁棒性；2)网络结构相对简单，在保持准确度相当的情况下，计算效率更高；3)首次使用层次分类的方法对车辆进行细粒度分类，使得单一网络能同时用于识别汽车类型、生产商、汽车型号和生产年份。在Compcars和Stanford Cars标准数据集上进行实验。结果表明，与现存方法相比，FACR在计算效率和分类精度方面具有良好性能。
Most existing fine-grained car recognizers have achieved the good performances on various datasets. However, these recognizers usually work inefficiently, and attention regions cannot be accurately localized especially when multiple cars exist. In this work, we propose a fast and accurate car recognizer called FACR, and it has three advantages over the previous approaches as follows. 1) The attention region localization component proposed in this work has high robustness to the background noise in the image. 2) The network structure proposed in this work is relatively simple, and it has higher computational efficiency while maintaining near accuracy. 3) It is the first time to use the hierarchical classification to finely and accurately categorize cars, and to allow a single network to simultaneously recognize car types, manufacturers, car models, and years of manufacture. The experiments are carried out on standard datasets Compcars and Stanford Cars, and the results demonstrate that FACR achieves the competitive performance compared with the-state-of-art methods in terms of both computational efficiency and classification accuracy.
[1] Zhang X P, Xiong H K, Zhou W G, et al. Picking deep filter responses for fine-grained image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2016:1134-1142.
[2] Reed S, Akata Z, Lee H, et al. Learning deep representations of fine-grained visual descriptions[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2016:49-58.
[3] Fu J L, Zheng H L, Mei T. Look closer to see better:recurrent attention convolutional neural network for fine-grained image recognition[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2017:4476-4484.
[4] Yu Y, Jin Q, Chen C W. FF-cmnet:a cnn-based model for fine-grained classification of car models based on feature fusion[C]//2018 IEEE International Conference on Multimedia and Expo. IEEE Computer Society, 2018:1-6.
[5] Khosla A, Jayadevaprakash N, Yao B P, et al. Novel dataset for fine-grained image categorization:stanford dogs[C/OL]. (2011-06-20)[2019-05-17]. http://people.csail.mit.edu/khosla/papers/fgvc2011.pdf.
[6] Yang L J, Luo P, Loy C C, et al. A large-scale car dataset for fine-grained categorization and verification[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2015:3973-3981.
[7] Liu X, Xia T, Wang J, et al. Fully convolutional attention networks for fine-grained recognition[C/OL]. arXiv:1603.06765v4, 2017.[2019-04-27]. http://arxiv.org/abs/1603.06765.
[8] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2016:770-778.
[9] He X T, Peng Y X. Fine-grained image classification via combining vision and language[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2017:7332-7340.
[10] Redmon J, Farhadi A. Yolo9000:better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2017:6517-6525.
[11] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C/OL]. arXiv:1409.1556, 2015.[2019-04-20]. https://arxiv.org/abs/1409.1556.
[12] Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252.
[13] Redmon J, Farhadi A. Yolov3:an incremental improvement[C/OL]. arXiv:1804.02767, 2018.[2019-04-20]. http://arxiv.org/abs/1804.02767.
[14] Krause J, Stark M, Deng J, et al. 3d object representations for fine-grained categorization[C]//2013 IEEE International Conference on Computer Vision Workshops. IEEE Computer Society, 2013:554-561.
[15] Sermanet P, Frome A, Real E. Attention for fine-grained categorization[C/OL]. arXiv:1412.7054, 2015.[2019-04-20]. https://arxiv.org/abs/1412.7054.
[16] Krause J, Jin H L, Yang J C, et al. Fine-grained recognition without part annotations[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2015:5546-5555.
[17] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014:580-587.
[18] Zhao B, Wu X, Feng J S, et al. Diversified visual attention networks for fine-grained object classification[J]. IEEE Trans Multimedia, 2017, 19(6):1245-1256.
[19] Lin T Y, Roychowdhury A, Maji S. Bilinear convolutional neural networks for fine-grained visual recognition[J]. IEEE Trans Pattern Anal Mach Intell, 2018, 40(6):1309-1322.
[20] Hu Q C, Wang H B, Li T, et al. Deep CNNs with spatially weighted pooling for fine-grained car recognition[J]. IEEE Trans Intelligent Transportation Systems, 2017, 18(11):3147-3156.
