Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance

by   Saptarshi Sinha, et al.

Class-imbalance is one of the major challenges in real world datasets, where a few classes (called majority classes) constitute much more data samples than the rest (called minority classes). Learning deep neural networks using such datasets leads to performances that are typically biased towards the majority classes. Most of the prior works try to solve class-imbalance by assigning more weights to the minority classes in various manners (e.g., data re-sampling, cost-sensitive learning). However, we argue that the number of available training data may not be always a good clue to determine the weighting strategy because some of the minority classes might be sufficiently represented even by a small number of training data. Overweighting samples of such classes can lead to drop in the model's overall performance. We claim that the 'difficulty' of a class as perceived by the model is more important to determine the weighting. In this light, we propose a novel loss function named Class-wise Difficulty-Balanced loss, or CDB loss, which dynamically distributes weights to each sample according to the difficulty of the class that the sample belongs to. Note that the assigned weights dynamically change as the 'difficulty' for the model may change with the learning progress. Extensive experiments are conducted on both image (artificially induced class-imbalanced MNIST, long-tailed CIFAR and ImageNet-LT) and video (EGTEA) datasets. The results show that CDB loss consistently outperforms the recently proposed loss functions on class-imbalanced datasets irrespective of the data type (i.e., video or image).


page 1

page 2

page 3

page 4


Class-Difficulty Based Methods for Long-Tailed Visual Recognition

Long-tailed datasets are very frequently encountered in real-world use c...

Enhancement Encoding: A New Imbalanced Classification Approach via Encoding the Labels

Class imbalance, which is also called long-tailed distribution, is a com...

Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation

An unbiased scene graph generation (SGG) algorithm referred to as Skew C...

Class-Balanced Loss Based on Effective Number of Samples

With the rapid increase of large-scale, real-world datasets, it becomes ...

Two-phase training mitigates class imbalance for camera trap image classification with CNNs

By leveraging deep learning to automatically classify camera trap images...

Understanding CNN Fragility When Learning With Imbalanced Data

Convolutional neural networks (CNNs) have achieved impressive results on...

Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning

Class imbalance distribution widely exists in real-world engineering. Ho...

Please sign up or login with your details

Forgot password? Click here to reset