通过基于风格迁移的增量数据增强提升新环境中的视觉感知
Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfer
AI总结：
本文提出利用 VPE 识别新颖输入，并通过神经风格迁移进行增量数据增强，实验证明该方法能显著提升模型在新颖环境下的视觉感知鲁棒性。
摘要：
自主智能体在真实场景中的部署受到“未知的未知”的挑战，即训练期间未遇到的新颖意外环境，例如退化的标志。虽然现有研究侧重于异常检测和类别不平衡，但往往无法应对真正新颖的场景。我们的方法通过利用 Variational Prototyping Encoder (VPE) 来增强视觉感知，以熟练地识别和处理新颖输入，然后使用神经风格迁移增量地增强数据，以丰富代表性不足的数据。通过比较仅在原始数据集上训练的模型与在原始数据集和增强数据集组合上训练的模型，我们观察到后者性能有显著提升。这强调了数据增强在增强模型鲁棒性方面的关键作用。我们的研究结果表明，将生成模型纳入特定领域增强策略具有潜在益处。
英文摘要：
The deployment of autonomous agents in real-world scenarios is challenged by "unknown unknowns", i.e. novel unexpected environments not encountered during training, such as degraded signs. While existing research focuses on anomaly detection and class imbalance, it often fails to address truly novel scenarios. Our approach enhances visual perception by leveraging the Variational Prototyping Encoder (VPE) to adeptly identify and handle novel inputs, then incrementally augmenting data using neural style transfer to enrich underrepresented data. By comparing models trained solely on original datasets with those trained on a combination of original and augmented datasets, we observed a notable improvement in the performance of the latter. This underscores the critical role of data augmentation in enhancing model robustness. Our findings suggest the potential benefits of incorporating generative models for domain-specific augmentation strategies.
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。
