6 papers
Respect Your Zero-Shot Uncertainty: Conservative Calibration for Test-Time-Adapted Vision-Language Models
Jingyan Jiang, Yaru Sun, Xiao Chen +5
Test-time adaptation (TTA) can improve the recognition accuracy of vision-language models under distribution shift, but often degrades calibration, making predictive confidence unr…
Beyond First-Order: Learning Riemannian Geometries for Invariant Visual Place Recognition
Jintao Cheng, Weibin Li, Zhijian He +3
Visual Place Recognition (VPR) demands representations robust to drastic environmental and viewpoint shifts. Existing aggregation paradigms either depend on extensive supervised tr…
Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
Zhijian He, Feifei Liu, Yuwei Li +4
Multi-modal 3D object detection is important for reliable perception in robotics and autonomous driving. However, its effectiveness remains limited under adverse weather conditions…
Beyond ADE and FDE: A Comprehensive Evaluation Framework for Safety-Critical Prediction in Multi-Agent Autonomous Driving Scenarios
Feifei Liu, Haozhe Wang, Zejun Wei +5
Current evaluation methods for autonomous driving prediction models rely heavily on simplistic metrics such as Average Displacement Error (ADE) and Final Displacement Error (FDE).…
Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time
Jintao Cheng, Weibin Li, Jiehao Luo +5
Visual Place Recognition (VPR) has evolved from handcrafted descriptors to deep learning approaches, yet significant challenges remain. Current approaches, including Vision Foundat…
KDMOS:Knowledge Distillation for Motion Segmentation
Chunyu Cao, Jintao Cheng, Zeyu Chen +4
Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction…