Single-Shot Refinement Neural Network for Object Detection

By Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, S. Li. 2017

1,373 citations recorded by the source corpus.

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 accuracy 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 multitask 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 https://github.com/sfzhang15/RefineDet.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, background): “Thereafter, plenty of works are presented to boost its performance in different aspects, such as fusing context information from different layers [24, 12, 69], training from scratch [50, 73], introducing new loss function [33, 6], anchor refinement and matching [66, 67], architecture redesign [21, 2”
Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “RefineDet [65] added an anchor refinement module to the single-shot SSD [40], to improve localization accuracy.”
Objects as Points (2019, neutral): “2 RefineDet [59] ResNet-101 - 36.”
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (2020, neutral): “Model AP50 AP RefineDet512+ [68] 83.”
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019, background): “2 RefineDet R-101 [41] 832× 500 90 (Titan X) 34.”
Class-incremental Learning via Deep Model Consolidation (2019, methodology): “We perform all experiments using RetinaNet [30], but the proposed method is applicable to other one-stage detectors [32, 43, 54, 25] with minor modifications.”
CornerNet: Detecting Objects as Paired Keypoints (2018, neutral): “2 - - - - - RefineDet512 (multi scale) (Zhang et al., 2017) ResNet-101 41.”
Deep High-Resolution Representation Learning for Visual Recognition (2019, neutral): “RefineDet [177] ResNet-101 512 36.”
CenterNet: Keypoint Triplets for Object Detection (2019, background): “, RetinaNet800 [25] and RefineDet [48]).”
Scale-Aware Trident Networks for Object Detection (2019, methodology): “Inheriting the merits of two-stage approaches, RefineDet [42] proposes an anchor refinement module to first filter the negative anchor boxes and coarsely adjust the anchor boxes for the next detection module.”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, neutral): “Single-shot refinement neural network for object detection [95] RefineDet VGG-16 320 38.”
Region Proposal by Guided Anchoring (2019, background): “There have been attempts [8, 9, 23, 31, 33, 34, 1, 2] that apply cascade architecture to reject easy samples at early layers or stages, and regress bounding boxes iteratively for progressive refinement.”
Bottom-Up Object Detection by Grouping Extreme and Center Points (2019, background): “2 RefineDet (SS) [52] ResNet-101 512× 512 36.”
Feature Selective Anchor-Free Module for Single-Shot Object Detection (2019, neutral): “4 RefineDet [37] (multi-scale) 41.”
Deep Feature Pyramid Reconfiguration for Object Detection (2018, background): “Several works are trying to develop more suitable connection manners [25,46,48], or to add more operations before combination [28].”
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (2019, methodology): “The same idea is also used in single-stage detectors, such as RefineDet [42].”
A Survey of Deep Learning-Based Object Detection (2019, background): “[36] present a novel RefineDet which achieves”
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation (2020, background): “Over the past few years, deep neural network (DNN) significantly pushed forward the state-of-the-art in several tasks in computer vision field, such as object detection [31,44], instance segmentation [11,10], and semantic segmentation [27,2].”
Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving (2019, methodology): “In recent years, to take advantage of both types of method and to compensate for their respective disadvantages, object detectors combining various schemes have been widely studied [1, 11, 29, 28, 16].”
Probabilistic Anchor Assignment with IoU Prediction for Object Detection (2020, methodology): “Since the seminal work of R-CNN [8], recent advances in object detection have shown rapid improvements with many innovative architectural designs [21,28,41,43], training objectives [3, 7, 22, 29] and post-processing schemes [2, 13, 15] with strong CNN backbones [5,11,17,19,31,32,36].”