Centralized Feature Pyramid for Object Detection

TL;DR

This paper introduces a Centralized Feature Pyramid (CFP) that enhances object detection by explicitly regulating intra-layer features using global and local visual centers, leading to improved performance on MS-COCO benchmarks.

Contribution

The paper proposes a novel CFP method that captures global long-range dependencies and local corner regions for better feature representation in object detection.

Findings

CFP improves detection accuracy on MS-COCO.

CFP outperforms existing feature pyramids in experiments.

CFP enhances YOLOv5 and YOLOX baselines with consistent gains.

Abstract

Visual feature pyramid has shown its superiority in both effectiveness and efficiency in a wide range of applications. However, the existing methods exorbitantly concentrate on the inter-layer feature interactions but ignore the intra-layer feature regulations, which are empirically proved beneficial. Although some methods try to learn a compact intra-layer feature representation with the help of the attention mechanism or the vision transformer, they ignore the neglected corner regions that are important for dense prediction tasks. To address this problem, in this paper, we propose a Centralized Feature Pyramid (CFP) for object detection, which is based on a globally explicit centralized feature regulation. Specifically, we first propose a spatial explicit visual center scheme, where a lightweight MLP is used to capture the globally long-range dependencies and a parallel learnable visual center mechanism is used to capture the local corner regions of the input images. Based on this, we then propose a globally centralized regulation for the commonly-used feature pyramid in a top-down fashion, where the explicit visual center information obtained from the deepest intra-layer feature is used to regulate frontal shallow features. Compared to the existing feature pyramids, CFP not only has the ability to capture the global long-range dependencies, but also efficiently obtain an all-round yet discriminative feature representation. Experimental results on the challenging MS-COCO validate that our proposed CFP can achieve the consistent performance gains on the state-of-the-art YOLOv5 and YOLOX object detection baselines.