A Class Imbalance Loss for Imbalanced Object Recognition

Abstract

The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the gradient. Hence, these datasets have a significantly negative impact on the performance of many stateof-the-art methods. In this article, we propose a class imbalance loss (CI loss) to handle this problem. To distinguish imbalanced datasets in accordance with the extent of imbalance, we also define an imbalance degree that works as a decision index factor in the CI loss. Because the minority classes with fewer samples probably lose chances in descending the gradient in the training process, CI loss is introduced to make these minority classes descend further than the majority classes. In view of the imbalanced distribution of data in few-shot learning, a method for generating an imbalanced few-shot learning dataset is presented in this article. We conducted a large number of experiments in the MiniImageNet dataset, which showed the effectiveness of an algorithm for model-agnostic metalearning for rapid adaptation with CI loss. In the problem of detecting 15 ship categories, our loss function is transplanted to a rotational region convolutional neural network detection method and a cascade network architecture and achieves higher mean average precision than focal loss and cross-entropy loss. In addition, the Mixed National Institute of Standards and Technology dataset and the Moving and Stationary Target Acquisition and Recognition dataset are sampled to imbalance datasets to verify the effectiveness of CI loss.

BBW: a batch balance wrapper for training deep neural networks on extremely imbalanced datasets with few minority samples

“…The aim was to compare the performance of BBW with six popular imbalanced data processing methods, using the same datasets and the same underlying model: down sampling [3], oversampling [4], class weights [1], focal loss [9], weighted softmax loss (WSL) [11], and class imbalance loss (CIL) [12]. All three datasets were used: CHB-MIT, BonnEEG and FAHXJU.…”

“…Jia et al [11] propose weighted softmax loss, adaptively parameterized by maximum multi-class imbalance ratio. Zhang et al [12] devise class imbalance loss to improve the cross-entropy loss on imbalanced datasets.…”

“…Recently, imbalanced dataset processing methods have been specifically designed for deep learning, for example those based on loss functions such as focal loss [9], gradient harmonizing [10], weighted softmax loss [11] and class imbalance loss [12]. Modified optimizer methods [13] are another technical solution, such as DM-SGD [14] and ABSGD [15].…”

“…Second, we compared BBW to the baseline using the proposed modified leave-one-out method for cross-validation. Third, BBW was compared to six existing approaches (down sampling [3], oversampling [4], class weights [1], focal loss [9], weighted softmax loss (WSL) [11], and class imbalance loss (CIL) [12]) for training with unbalanced data. Fourth, we carried out an ablation study to show the contribution of different parts of the BBW framework.…”

SAR Target Classification Based on Integration of ASC Parts Model and Deep Learning Algorithm

“…The final output of the proposed method is the mean of two probability distribution vectors. In this paper, the cross entropy loss [50] is used to calculate the error for backward propagation, and the stochastic gradient descent (SGD) [51] is used to optimize parameters. During the test process, parameters of the ASC model and parts images of each test target also need to be calculated at first.…”