Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Beyond One-Hot Labels: Semantic Mixing for Model Calibration
Haoyang Luo, Linwei Tao, Minjing Dong +1
Model calibration seeks to ensure that models produce confidence scores that accurately reflect the true likelihood of their predictions being correct. However, existing calibratio…
cs.CV2025
Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
Younan Zhu, Linwei Tao, Minjing Dong +1
Large Vision-Language Models (LVLMs) exhibit impressive multimodal reasoning capabilities but remain highly susceptible to object hallucination, where models generate responses tha…
cs.CV2024
Feature Clipping for Uncertainty Calibration
Linwei Tao, Minjing Dong, Chang Xu
Deep neural networks (DNNs) have achieved significant success across various tasks, but ensuring reliable uncertainty estimates, known as model calibration, is crucial for their sa…