TY - JOUR AU - Idoia Ruiz AU - Joan Serrat PY - 2022// TI - Hierarchical Novelty Detection for Traffic Sign Recognition T2 - SENS JO - Sensors SP - 4389 VL - 22 IS - 12 KW - Novelty detection KW - hierarchical classification KW - deep learning KW - traffic sign recognition KW - autonomous driving KW - computer vision N2 - Recent works have made significant progress in novelty detection, i.e., the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes. However, the only information this task provides about novel samples is that they are unknown. In this work, we leverage hierarchical taxonomies of classes to provide informative outputs for samples of novel classes. We predict their closest class in the taxonomy, i.e., its parent class. We address this problem, known as hierarchical novelty detection, by proposing a novel loss, namely Hierarchical Cosine Loss that is designed to learn class prototypes along with an embedding of discriminative features consistent with the taxonomy. We apply it to traffic sign recognition, where we predict the parent class semantics for new types of traffic signs. Our model beats state-of-the art approaches on two large scale traffic sign benchmarks, Mapillary Traffic Sign Dataset (MTSD) and Tsinghua-Tencent 100K (TT100K), and performs similarly on natural images benchmarks (AWA2, CUB). For TT100K and MTSD, our approach is able to detect novel samples at the correct nodes of the hierarchy with 81% and 36% of accuracy, respectively, at 80% known class accuracy. UR - http://dx.doi.org/10.3390/s22124389 N1 - ADAS; 600.154 ID - Idoia Ruiz2022 ER -