自监督学习探索:面向目标分类的数据集组成测试
Explorations in Self-Supervised Learning: Dataset Composition Testing for Object Classification
AI总结:
本文通过从 Omnidata 采样不同特征数据并预训练 SimCLR,再迁移至 Resnet-50,揭示模态、分辨率与亮度对 SSL 目标分类性能的影响。
摘要:
本文研究了使用具有不同图像特征的数据集进行采样和预训练,对目标分类自监督学习(SSL)模型性能的影响。为此,作者基于模态、亮度、图像尺寸和相机视场,从 Omnidata 平台采样两个公寓数据集,并用它们预训练 SimCLR 模型。随后,预训练模型生成的编码被迁移到用于目标分类的有监督 Resnet-50 模型。通过 A/B 测试,作者发现深度预训练模型在低分辨率图像上更有效,而 RGB 预训练模型在较高分辨率图像上表现更好。研究还发现,提高训练图像亮度可以改善模型在低分辨率图像上的性能,同时不会对其在较高分辨率图像上的性能产生负面影响。
英文摘要:
This paper investigates the impact of sampling and pretraining using datasets with different image characteristics on the performance of self-supervised learning (SSL) models for object classification. To do this, we sample two apartment datasets from the Omnidata platform based on modality, luminosity, image size, and camera field of view and use them to pretrain a SimCLR model. The encodings generated from the pretrained model are then transferred to a supervised Resnet-50 model for object classification. Through A/B testing, we find that depth pretrained models are more effective on low resolution images, while RGB pretrained models perform better on higher resolution images. We also discover that increasing the luminosity of training images can improve the performance of models on low resolution images without negatively affecting their performance on higher resolution images.
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。