Abstract

Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. All state-of-the-art object detection systems still rely on recognizing object instances individually, without exploiting their relations during learning. This work proposes an object relation module. It processes a set of objects simultaneously through interaction between their appearance feature and geometry, thus allowing modeling of their relations. It is lightweight and in-place. It does not require additional supervision and is easy to embed in existing networks. It is shown effective on improving object recognition and duplicate removal steps in the modern object detection pipeline. It verifies the efficacy of modeling object relations in CNN based detection. It gives rise to the first fully end-to-end object detector.

Keywords

Computer scienceObject (grammar)Relation (database)Object detectionArtificial intelligencePipeline (software)MethodSpatial relationSet (abstract data type)Cognitive neuroscience of visual object recognitionFeature (linguistics)Computer visionObject modelViola–Jones object detection frameworkObject relations theoryFeature extractionPattern recognition (psychology)Object-oriented programmingData miningProgramming language

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
article
Pages
3588-3597
Citations
1493
Access
Closed

External Links

Download PDF (Free) View on DOI.org arXiv Semantic Scholar

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1493
OpenAlex
95
Influential
1046
CrossRef

Cite This

Han Hu, Jiayuan Gu, Zheng Zhang et al. (2018). Relation Networks for Object Detection. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition , 3588-3597. https://doi.org/10.1109/cvpr.2018.00378

Identifiers

DOI
10.1109/cvpr.2018.00378
arXiv
1711.11575

Data Quality

Data completeness: 84%