DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection

TL;DR

This paper introduces DC-SPP-YOLO, an improved object detection model that enhances YOLOv2's accuracy by integrating dense connections and an advanced spatial pyramid pooling, resulting in higher mAP on standard datasets.

Contribution

The paper proposes a novel YOLO variant with dense connections and improved spatial pyramid pooling to boost detection accuracy over YOLOv2.

Findings

Higher mAP on PASCAL VOC dataset

Improved feature extraction with dense connections

Enhanced multi-scale feature utilization

Abstract

Although the YOLOv2 method is extremely fast on object detection, its detection accuracy is restricted due to the low performance of its backbone network and the underutilization of multi-scale region features. Therefore, a dense connection (DC) and spatial pyramid pooling (SPP) based YOLO (DC-SPP-YOLO) method for ameliorating the object detection accuracy of YOLOv2 is proposed in this paper. Specifically, the dense connection of convolution layers is employed in the backbone network of YOLOv2 to strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an improved spatial pyramid pooling is introduced to pool and concatenate the multi-scale region features, so that the network can learn the object features more comprehensively. The DC-SPP-YOLO model is established and trained based on a new loss function composed of MSE (mean square error) loss and cross-entropy loss. The experimental results indicated that the mAP (mean Average Precision) of DC-SPP-YOLO is higher than that of YOLOv2 on the PASCAL VOC datasets and the UA-DETRAC datasets. The effectiveness of DC-SPP-YOLO method proposed is demonstrated.