Differential Feature Fusion, Triplet Global Attention, and Web Semantic for Pedestrian Detection

Abstract

In complex environments and crowded pedestrian scenes, the overlap or loss of local features is a pressing issue. However, existing methods often struggle to strike a balance between eliminating interfering features and establishing feature connections. To address this challenge, we introduce a novel pedestrian detection approach called Differential Feature Fusion under Triplet Global Attention (DFFTGA). This method merges feature maps of the same size from different stages to introduce richer feature information. Specifically, we introduce a pixel-level Triplet Global Attention (TGA) module to enhance feature representation and perceptual range. Additionally, we introduce a Differential Feature Fusion (DFF) module, which optimizes features between similar nodes for filtering. This series of operations helps the model focus more on discriminative features, ultimately improving pedestrian detection performance. Compared to benchmarks, we achieve significant improvements and demonstrate outstanding performance on datasets such as CityPersons and CrowdHuman.