arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.04181cs.CVcs.LG
收藏

TransformNet:通过预测几何变换的自监督表示学习

TransformNet: Self-supervised representation learning through predicting geometric transformations

Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Sayed Hashim, Muhammad Ali

摘要:

深度神经网络需要大量的训练数据,而在现实世界中,可用于训练目的的数据稀缺。为了解决这个问题,使用无监督方法来训练有限的数据。在这份报告中,我们描述了无监督的语义特征学习方法,用于识别应用于输入数据的几何变换。我们方法的基本概念是,如果某人不知道图像中的对象,他/她将无法定量预测应用于它们的几何变换。该自监督机制基于前置任务和下游任务。量化几何变换的借口分类任务应该迫使CNN学习对图像分类有用的对象的高级显著特征。在我们的基线模型中,我们将图像旋转定义为90度的倍数。在此前提任务上训练的CNN将用于CIFAR-10数据集中的图像分类,作为下游任务。我们使用各种模型运行基线方法,包括ResNet,DenseNet,VGG-16和NIN,在特征提取和微调设置中具有不同的旋转次数。在这个基线模型的扩展中,我们在借口任务中尝试了旋转以外的变换。我们比较了所选模型在各种设置中的性能,这些设置具有应用于图像的不同变换、各种数据增强技术以及使用不同的优化器。这一系列不同类型的实验将帮助我们证明我们的自监督模型在应用于下游分类任务时的识别准确性。

英文摘要:

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this report, we describe the unsupervised semantic feature learning approach for recognition of the geometric transformation applied to the input data. The basic concept of our approach is that if someone is unaware of the objects in the images, he/she would not be able to quantitatively predict the geometric transformation that was applied to them. This self supervised scheme is based on pretext task and the downstream task. The pretext classification task to quantify the geometric transformations should force the CNN to learn high-level salient features of objects useful for image classification. In our baseline model, we define image rotations by multiples of 90 degrees. The CNN trained on this pretext task will be used for the classification of images in the CIFAR-10 dataset as a downstream task. we run the baseline method using various models, including ResNet, DenseNet, VGG-16, and NIN with a varied number of rotations in feature extracting and fine-tuning settings. In extension of this baseline model we experiment with transformations other than rotation in pretext task. We compare performance of selected models in various settings with different transformations applied to images,various data augmentation techniques as well as using different optimizers. This series of different type of experiments will help us demonstrate the recognition accuracy of our self-supervised model when applied to a downstream task of classification.

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。

↑