Object Detection Networks on Convolutional Feature Maps

Abstract

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important. We experiment with region-wise classifier networks that use shared, region-independent convolutional features. We call them "Networks on Convolutional feature maps" (NoCs). We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier. We show by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015.

Keywords

Classifier (UML)Computer scienceExtractorConvolutional neural networkArtificial intelligencePattern recognition (psychology)Object detectionDeep learningPerceptronFeature extractionFeature (linguistics)Artificial neural networkEngineering

Related Publications

Fast R-CNN

Ross Girshick

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposa...

2015 2015 IEEE International Conference on... 26511 citations

Fast R-CNN

Ross Girshick

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposa...

2015 arXiv (Cornell University) 1766 citations

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Shaoqing Ren , Kaiming He , Ross Girshick +1 more

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running tim...

2015 arXiv (Cornell University) 18214 citations

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks

Shaoqing Ren , Kaiming He , Ross Girshick +1 more

State-of-the-art object detection networks depend on region proposal\nalgorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN\nhave reduced the running t...

2015 arXiv (Cornell University) 6211 citations

Feature Pyramid Networks for Object Detection

Tsung-Yi Lin , Piotr Dollár , Ross Girshick +3 more

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors...

2017 2017 IEEE Conference on Computer Visi... 26836 citations

Publication Info

Year: 2015
Type: preprint
Citations: 35
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Object Detection Networks on Convolutional Feature Maps

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

OpenAlex

Cite This

APA Style

                            
                                    Shaoqing Ren, 
                                
                                    Kaiming He, 
                                
                                    Ross Girshick
                                
                                et al.
                            
                            (2015). 
                            Object Detection Networks on Convolutional Feature Maps. 
                            arXiv (Cornell University)
                            
                            .
                            https://doi.org/10.48550/arxiv.1504.06066

Identifiers

DOI: 10.48550/arxiv.1504.06066