arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.14829cs.CV
收藏

通过分析CNN培训分数缓解数据集偏倚

Dataset Bias Mitigation Through Analysis of CNN Training Scores

Sabancı University(萨班哲大学)

Ekberjan Derman

摘要:

训练数据集对于基于卷积神经网络的算法至关重要,直接影响其整体性能。因此,使用具有最小偏差水平的结构良好的数据集总是可取的。在本文中,我们提出了一种新的,独立于域的方法,称为基于分数的响应(SBR),根据该训练集获得的模型预测分数来定位原始训练数据集的代表性不足的样本。在我们的方法中,一旦经过训练,我们使用相同的CNN模型来推断自己的训练样本,获得预测分数,并根据预测和地面实况之间的距离,识别远离其地面实况的样本,并在原始训练集中对其进行增强。降低了Sigmoid函数的温度项,以更好地区分分数。为了进行实验评估,我们选择了一个Kaggle数据集进行性别分类。我们首先使用一个基于CNN的分类器,具有相对标准的结构,在训练图像上进行训练,并在原始数据集的验证样本上进行评估。然后,我们在一个全新的测试数据集上进行了评估,该数据集由浅色男性、浅色女性、深色男性和深色女性组成。所获得的准确性各不相同,揭示了原始数据集中存在对某些群体的分类偏见。随后,我们根据我们提出的方法训练了重新训练后的模型。我们比较了我们的方法与以前提出的变分自编码器(VAE)为基础的算法。实验结果证实了该方法的有效性,该方法可以在原始数据集中重新识别代表性不足的样本,以减少对某些群体的分类偏差。虽然测试性别分类,所提出的算法可以用于调查任何基于CNN的任务的数据集结构。

英文摘要:

Training datasets are crucial for convolutional neural network-based algorithms, which directly impact their overall performance. As such, using a well-structured dataset that has minimum level of bias is always desirable. In this paper, we proposed a novel, domain-independent approach, called score-based resampling (SBR), to locate the under-represented samples of the original training dataset based on the model prediction scores obtained with that training set. In our method, once trained, we use the same CNN model to infer on its own training samples, obtain prediction scores, and based on the distance between predicted and ground-truth, we identify samples that are far away from their ground-truth and augment them in the original training set. The temperature term of the Sigmoid function is decreased to better differentiate scores. For experimental evaluation, we selected one Kaggle dataset for gender classification. We first used a CNN-based classifier with relatively standard structure, trained on the training images, and evaluated on the provided validation samples of the original dataset. Then, we assessed it on a totally new test dataset consisting of light male, light female, dark male, and dark female groups. The obtained accuracies varied, revealing the existence of categorical bias against certain groups in the original dataset. Subsequently, we trained the model after resampling based on our proposed approach. We compared our method with a previously proposed variational autoencoder (VAE) based algorithm. The obtained results confirmed the validity of our proposed method regrading identifying under-represented samples among original dataset to decrease categorical bias of classifying certain groups. Although tested for gender classification, the proposed algorithm can be used for investigating dataset structure of any CNN-based tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑