Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. / Cui, Yin; Song, Yang; Sun, Chen; Howard, Andrew; Belongie, Serge.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 14.12.2018, p. 4109-4118.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
AU - Cui, Yin
AU - Song, Yang
AU - Sun, Chen
AU - Howard, Andrew
AU - Belongie, Serge
N1 - Publisher Copyright: © 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make & model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.
AB - Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make & model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.
UR - http://www.scopus.com/inward/record.url?scp=85056150918&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00432
DO - 10.1109/CVPR.2018.00432
M3 - Conference article
AN - SCOPUS:85056150918
SP - 4109
EP - 4118
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -
ID: 301825551