Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution

by   Jiahao Chen, et al.

How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ignore the fact that real-world data often follows a long-tailed distribution. In this paper, we explore the problem of calibrating the model trained from a long-tailed distribution. Due to the difference between the imbalanced training distribution and balanced test distribution, existing calibration methods such as temperature scaling can not generalize well to this problem. Specific calibration methods for domain adaptation are also not applicable because they rely on unlabeled target domain instances which are not available. Models trained from a long-tailed distribution tend to be more overconfident to head classes. To this end, we propose a novel knowledge-transferring-based calibration method by estimating the importance weights for samples of tail classes to realize long-tailed calibration. Our method models the distribution of each class as a Gaussian distribution and views the source statistics of head classes as a prior to calibrate the target distributions of tail classes. We adaptively transfer knowledge from head classes to get the target probability density of tail classes. The importance weight is estimated by the ratio of the target probability density over the source probability density. Extensive experiments on CIFAR-10-LT, MNIST-LT, CIFAR-100-LT, and ImageNet-LT datasets demonstrate the effectiveness of our method.


page 2

page 7


Label-Aware Distribution Calibration for Long-tailed Classification

Real-world data usually present long-tailed distributions. Training on i...

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Object frequency in the real world often follows a power law, leading to...

General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone

Facial age estimation has received a lot of attention for its diverse ap...

Balanced Product of Experts for Long-Tailed Recognition

Many real-world recognition problems suffer from an imbalanced or long-t...

Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation

Deep neural networks have made huge progress in the last few decades. Ho...

Open Long-Tailed Recognition in a Dynamic World

Real world data often exhibits a long-tailed and open-ended (with unseen...

Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification

We address the overlooked unbiasedness in existing long-tailed classific...

Please sign up or login with your details

Forgot password? Click here to reset