Disentangling Label Distribution for Long-tailed Visual Recognition

by   Youngkyu Hong, et al.

The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable practicality since the target may also be long-tailed. Therefore, we formulate long-tailed visual recognition as a label shift problem where the target and source label distributions are different. One of the significant hurdles in dealing with the label shift problem is the entanglement between the source label distribution and the model prediction. In this paper, we focus on disentangling the source label distribution from the model prediction. We first introduce a simple baseline method that matches the target label distribution by post-processing the model prediction trained by the cross-entropy loss and the Softmax function. Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase. Thus, we propose a novel method, LAbel distribution DisEntangling (LADE) loss based on the optimal bound of Donsker-Varadhan representation. LADE achieves state-of-the-art performance on benchmark datasets such as CIFAR-100-LT, Places-LT, ImageNet-LT, and iNaturalist 2018. Moreover, LADE outperforms existing methods on various shifted target label distributions, showing the general adaptability of our proposed method.



There are no comments yet.


page 8

page 14


Balanced Meta-Softmax for Long-Tailed Visual Recognition

Deep classifiers have achieved great success in visual recognition. Howe...

Balanced Activation for Long-tailed Visual Recognition

Deep classifiers have achieved great success in visual recognition. Howe...

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

Real-world data universally confronts a severe class-imbalance problem a...

Is Importance Weighting Incompatible with Interpolating Classifiers?

Importance weighting is a classic technique to handle distribution shift...

Learning of Visual Relations: The Devil is in the Tails

Significant effort has been recently devoted to modeling visual relation...

Distilling Virtual Examples for Long-tailed Recognition

In this paper, we tackle the long-tailed visual recognition problem from...

Long-tailed Distribution Adaptation

Recognizing images with long-tailed distributions remains a challenging ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.