Abstract

It is well known that contextual and multi-scale representations are important for accurate visual recognition. In this paper we present the Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest. Contextual information outside the region of interest is integrated using spatial recurrent neural networks. Inside, we use skip pooling to extract information at multiple scales and levels of abstraction. Through extensive experiments we evaluate the design space and provide readers with an overview of what tricks of the trade are important. ION improves state-of-the-art on PASCAL VOC 2012 object detection from 73.9% to 77.9% mAP. On the new and more challenging MS COCO dataset, we improve state-of-the-art from 19.7% to 33.1% mAP. In the 2015 MS COCO Detection Challenge, our ION model won "Best Student Entry" and finished 3rd place overall. As intuition suggests, our detection results provide strong evidence that context and multi-scale representations improve small object detection.

Keywords

PoolingComputer scienceObject detectionExploitPascal (unit)Artificial intelligenceIntuitionAbstractionArtificial neural networkContext (archaeology)Machine learningPattern recognition (psychology)Geography

Affiliated Institutions

Related Publications

Publication Info

Year
2016
Type
article
Citations
1297
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

1297
OpenAlex
113
Influential
914
CrossRef

Cite This

Sean Bell, C. Lawrence Zitnick, Kavita Bala et al. (2016). Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . https://doi.org/10.1109/cvpr.2016.314

Identifiers

DOI
10.1109/cvpr.2016.314
arXiv
1512.04143

Data Quality

Data completeness: 88%