IEEE

Contrastive-Learning-Based Adaptive Graph Fusion Convolution Network With Residual-Enhanced Decomposition Strategy for Traffic Flow Forecasting

Abstract: Traffic flow prediction is the foundation of traffic scheduling and a major component of intelligent transportation systems (ITSs). Accurate traffic flow prediction is crucial for numerous ...
IEEE

Diverse Branch Block: Building a Convolution as an Inception-like Unit

Abstract: We propose a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs. The block is named Diverse Branch Block (DBB), ...