论文标题
长期视觉位置识别的监督微调评估
Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition
论文作者
论文摘要
在本文中，我们介绍了一项有关深层卷积神经网络的实用性的全面研究，这些卷积神经网络具有两个最先进的合并层，它们是在卷积层之后放置的，并以端到端的方式进行了微调，以在挑战性条件下进行视觉位置识别任务，包括季节性和照明变化。我们与三种不同的损失函数（例如三胞胎，对比度和弧形，用于根据部署过程中正确匹配的分数来学习体系结构的参数。为了验证结果的有效性，我们利用了两个现实世界数据集的室内和室外识别。我们的调查表明，以端到端方式进行的微调体系结构在室外的表现优于其他两种损失约1〜4％，而在室内数据集中，对于视觉位置识别任务，在室内数据集中，室内数据集的表现优于1〜2％。
In this paper, we present a comprehensive study on the utility of deep convolutional neural networks with two state-of-the-art pooling layers which are placed after convolutional layers and fine-tuned in an end-to-end manner for visual place recognition task in challenging conditions, including seasonal and illumination variations. We compared extensively the performance of deep learned global features with three different loss functions, e.g. triplet, contrastive and ArcFace, for learning the parameters of the architectures in terms of fraction of the correct matches during deployment. To verify effectiveness of our results, we utilized two real world datasets in place recognition, both indoor and outdoor. Our investigation demonstrates that fine tuning architectures with ArcFace loss in an end-to-end manner outperforms other two losses by approximately 1~4% in outdoor and 1~2% in indoor datasets, given certain thresholds, for the visual place recognition tasks.
