スタイル変換による漸進的データ拡張で未知環境の視覚認識を強化
Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfer
変分プロトタイピングエンコーダで未知入力を検出し、ニューラルスタイル変換で不足データを漸進的に拡張することで、未知環境での視覚認識性能を向上させる手法を提案。
著者: Abhibha Gupta, Rully Agus Hendrawan, Mansur Arief
分類: cs.CV, cs.RO
原文アブストラクト
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.
