# SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection Source: [SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection]() Collection index: [llms.txt]() Data updated: 2026-04-22T05:23:53.567Z Authors: Hao Vo, Khoa Vo, Thinh Phan, Ngo Xuan Cuong, Gianfranco Doretto, Hien Nguyen, Anh Nguyen, Ngan Le Published: 2026-04-20T16:28:01.000Z ## Abstract Camera-only 3D object detection has emerged as a cost-effective and scalable alternative to LiDAR for autonomous driving, yet existing methods primarily prioritize overall performance while overlooking the severe long-tail imbalance inherent in real-world datasets. In practice, many rare but safety-critical categories such as children, strollers, or emergency vehicles are heavily underrepresented, leading to biased learning and degraded performance. This challenge is further exacerbated by pronounced inter-class ambiguity (e.g., visually similar subclasses) and substantial intra-class diversity (e.g., objects varying widely in appearance, scale, pose, or context), which together hinder reliable long-tail recognition. In this work, we introduce SemLT3D, a Semantic-Guided Expert Distillation framework designed to enrich the representation space for underrepresented classes through semantic priors. SemLT3D consists of: (1) a language-guided mixture-of-experts module that routes 3D queries to specialized experts according to their semantic affinity, enabling the model to better disentangle confusing classes and specialize on tail distributions; and (2) a semantic projection distillation pipeline that aligns 3D queries with CLIP-informed 2D semantics, producing more coherent and discriminative features across diverse visual manifestations. Although motivated by long-tail imbalance, the semantically structured learning in SemLT3D also improves robustness under broader appearance variations and challenging corner cases, offering a principled step toward more reliable camera-only 3D perception. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Object Detection on nuScenes (val) (AP by Instance Count)](): 3D Object Detection; nuScenes (val); mAP (All): 41.1. - [3D Object Detection on Argoverse 2 (val)](): 3D Object Detection; Argoverse 2 (val); mAP: 25.9. - [3D Object Detection on nuScenes v1.0-trainval (val)](): 3D Object Detection; nuScenes v1.0-trainval (val); NDS: 42.79. ## Original sources and implementation [Original paper]() [PDF]()