Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving
This addresses the need for more interpretable and human-interactive anomaly detection in autonomous driving systems, though it is incremental by building on existing multimodal models.
The paper tackled the problem of out-of-distribution detection in autonomous driving by using language-based latent representations from CLIP to enhance transparency and controllability, resulting in improved detection performance compared to traditional vision encoders on realistic driving data.
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.