CNNs for Fine-Grained Car Model Classification
2020
This paper describes an end-to-end training methodology for CNN-based fine-grained vehicle model classification. The method relies exclusively on images, without using complicated architectures. No extra annotations, pose normalization or part localization are needed. Different full CNN-based models are trained and validated using CompCars [31] dataset, for a total of 431 different car models. We obtained a top-1 validation accuracy of 97.62% which substantially outperforms previous works.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
33
References
4
Citations
NaN
KQI