言語拡張潜在表現による自動運転の分布外検出
Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving
マルチモーダルモデルCLIPの画像・テキスト表現のコサイン類似度を潜在表現として用い、言語で定義可能な分布外検出を実現した研究。
著者: Zhenjiang Mao, Dong-You Jhong, Ao Wang, Ivan Ruchkin
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Out-of-distribution (OOD) detection is essential in autonomous driving, to determine when learning-based components encounter unexpected inputs. Traditional detectors typically use encoder models with fixed settings, thus lacking effective human interaction capabilities. With the rise of large foundation models, multimodal inputs offer the possibility of taking human language as a latent representation, thus enabling language-defined OOD detection. In this paper, we use the cosine similarity of image and text representations encoded by the multimodal model CLIP as a new representation to improve the transparency and controllability of latent encodings used for visual anomaly detection. We compare our approach with existing pre-trained encoders that can only produce latent representations that are meaningless from the user's standpoint. Our experiments on realistic driving data show that the language-based latent representation performs better than the traditional representation of the vision encoder and helps improve the detection performance when combined with standard representations.
