Scale-Transferrable Object Detection

Abstract

Scale problem lies in the heart of object detection. In this work, we develop a novel Scale-Transferrable Detection Network (STDN) for detecting multi-scale objects in images. In contrast to previous methods that simply combine object predictions from multiple feature maps from different network depths, the proposed network is equipped with embedded super-resolution layers (named as scale-transfer layer/module in this work) to explicitly explore the interscale consistency nature across multiple detection scales. Scale-transfer module naturally fits the base network with little computational cost. This module is further integrated with a dense convolutional network (DenseNet) to yield a one-stage object detector. We evaluate our proposed architecture on PASCAL VOC 2007 and MS COCO benchmark tasks and STDN obtains significant improvements over the comparable state-of-the-art detection models.

Keywords

Object detectionComputer sciencePascal (unit)Benchmark (surveying)Convolutional neural networkArtificial intelligenceScale (ratio)Feature extractionPattern recognition (psychology)Object (grammar)DetectorData mining

Affiliated Institutions

Shanghai Jiao Tong University CN

Related Publications

Single-Shot Refinement Neural Network for Object Detection

Shifeng Zhang , Longyin Wen , Xiao Bian +2 more

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 e...

2018 2018 IEEE/CVF Conference on Computer ... 1645 citations

Densely Connected Convolutional Networks

Gao Huang , Zhuang Liu , Laurens van der Maaten +1 more

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to ...

2017 42167 citations

Context Encoding for Semantic Segmentation

Hang Zhang , Kristin Dana , Jianping Shi +4 more

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous con...

2018 2018 IEEE/CVF Conference on Computer ... 1436 citations

M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network

Qijie Zhao , Tao Sheng , Yongtao Wang +4 more

Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R...

2019 Proceedings of the AAAI Conference on... 856 citations

Rethinking Atrous Convolution for Semantic Image Segmentation

Liang-Chieh Chen , George Papandreou , Florian Schroff +1 more

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep ...

2017 arXiv (Cornell University) 7401 citations

Publication Info

Year: 2018
Type: article
Pages: 528-537
Citations: 388
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Scale-Transferrable Object Detection

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

388

OpenAlex

Cite This

APA Style

                            
                                    Peng Zhou, 
                                
                                    Bingbing Ni, 
                                
                                    Cong Geng
                                
                                et al.
                            
                            (2018). 
                            Scale-Transferrable Object Detection. 
                            
                            , 528-537.
                            https://doi.org/10.1109/cvpr.2018.00062

Identifiers

DOI: 10.1109/cvpr.2018.00062