Deep Feature Pyramid Reconfiguration for Object Detection
This work addresses a known bottleneck in object detection for computer vision applications, offering an incremental improvement over existing feature pyramid designs.
The paper tackles inefficient semantic integration across scales in object detection feature pyramids by proposing a novel reconfiguration architecture with global attention and local reconfigurations, achieving consistent and significant boosts in the SSD system without losing real-time speed.
State-of-the-art object detectors usually learn multi-scale representations to get better results by employing feature pyramids. However, the current designs for feature pyramids are still inefficient to integrate the semantic information over different scales. In this paper, we begin by investigating current feature pyramids solutions, and then reformulate the feature pyramid construction as the feature reconfiguration process. Finally, we propose a novel reconfiguration architecture to combine low-level representations with high-level semantic features in a highly-nonlinear yet efficient way. In particular, our architecture which consists of global attention and local reconfigurations, is able to gather task-oriented features across different spatial locations and scales, globally and locally. Both the global attention and local reconfiguration are lightweight, in-place, and end-to-end trainable. Using this method in the basic SSD system, our models achieve consistent and significant boosts compared with the original model and its other variations, without losing real-time processing speed.