keyword

single-shot refinement neural network

A single-shot refinement neural network is an object detection architecture that combines the high processing speed of one-stage detectors with the accuracy of two-stage detectors by progressively refining bounding box proposals in an end-to-end framework. The network operates through two interconnected components: an anchor refinement module and an object detection module. The anchor refinement module filters out negative background anchors to shrink the search space and makes coarse adjustments to the anchor positions and sizes. These adjusted anchors and their feature representations are subsequently passed via transfer connection blocks to the object detection module, which performs fine bounding box regression and predicts multi-class categorization. By integrating coarse-to-fine localization and classification within a single feedforward pass, this approach mitigates class imbalance and localization errors while preserving real-time computational efficiency.

1 item

Single-Shot Refinement Neural Network for Object Detection

Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li

OrganizationsGeneral Electric CompanyInstitute of Automation, Chinese Academy of SciencesUniversity of Chinese Academy of Sciences

Why you should read this

Proposes RefineDet, an object detector that combines the high accuracy of two-stage methods with the fast inference of single-stage models by using anchor refinement and feature transfer modules to filter false positives and optimize bounding boxes before final classification.

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. RefineDet consists of two inter-connected modules, namely, the anchor refinement module and the object detection module. Specifically, the former aims to (1) filter out negative anchors to reduce search space for the classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes the refined anchors as the input from the former to further improve the regression and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO demonstrate that RefineDet achieves state-of-the-art detection accuracy with high efficiency. Code is available at this https URL

Source

https://arxiv.org/pdf/1711.06897

Added

2026-09-25