5 papers
Transformer Architectures as Complete Bayes Processes: A Formal Proof in the Measure-Theoretic Kernel Framework
Haobo Yang
We present a complete formal proof that transformer architectures, when their internal update mechanisms satisfy a Bayes joint-distribution condition, implement exact Bayesian post…
Stabilizing Information Flow Entropy: Regularization for Safe and Interpretable Autonomous Driving Perception
Haobo Yang, Shiyan Zhang, Zhuoyi Yang +3
Deep perception networks in autonomous driving traditionally rely on data-intensive training regimes and post-hoc anomaly detection, often disregarding fundamental information-theo…
Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
Haobo Yang, Minghao Guo, Dequan Yang +1
Contemporary deep learning models have achieved impressive performance in image classification by primarily leveraging statistical regularities within large datasets, but they rare…
Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving
Haobo Yang, Shiyan Zhang, Zhuoyi Yang +4
With the increasing complexity of the traffic environment, the significance of safety perception in intelligent driving is intensifying. Traditional methods in the field of intelli…
Gradient-Guided Parameter Mask for Multi-Scenario Image Restoration Under Adverse Weather
Jilong Guo, Haobo Yang, Mo Zhou +1
Removing adverse weather conditions such as rain, raindrop, and snow from images is critical for various real-world applications, including autonomous driving, surveillance, and re…