TY - GEN

T1 - Class-balanced loss based on effective number of samples

AU - Cui, Yin

AU - Jia, Menglin

AU - Lin, Tsung Yi

AU - Song, Yang

AU - Belongie, Serge

N1 - Funding Information: Our proposed framework provides a non-parametric means of quantifying data overlap, since we don’t make any assumptions about the data distribution. This makes our loss generally applicable to a wide range of existing models and loss functions. Intuitively, a better estimation of the effective number of samples could be obtained if we know the data distribution. In the future, we plan to extend our frame-work by incorporating reasonable assumptions on the data distribution or designing learning-based, adaptive methods. Acknowledgment. This work was supported in part by a Google Focused Research Award. Publisher Copyright: © 2019 IEEE.

PY - 2019/6

Y1 - 2019/6

N2 - With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re-weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula (1-beta {n})/(1-beta), where n is the number of samples and beta in [0,1) is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.

AB - With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re-weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula (1-beta {n})/(1-beta), where n is the number of samples and beta in [0,1) is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.

KW - Categorization

KW - Computer Vision Theory

KW - Deep Learning

KW - Recognition: Detection

KW - Retrieval

UR - http://www.scopus.com/inward/record.url?scp=85078723293&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2019.00949

DO - 10.1109/CVPR.2019.00949

M3 - Conference article

AN - SCOPUS:85078723293

SP - 9260

EP - 9269

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 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

Y2 - 16 June 2019 through 20 June 2019

ER -