Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,292

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

Open access
Bell, Sean, Zitnick, C. Lawrence, Bala, Kavita, Girshick, Ross·2016·2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2016.314
Open this paper in CoChat — free account

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2016.314

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 14 references

Research works printed but not linked: 31

  1. 10.1023/A:1023052124951 · DOI · Paper page
  2. 2010, U. the difficulty of training deep feedforward neural networks. Xavier glorot and yoshua bengio, AISTATS
  3. pont-tuset, 2015, Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
  4. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
  5. 10.1109/CVPR.2013.465 · DOI · Paper page
  6. sermanet, 2014, OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, ICLRE
  7. 10.1109/CVPR.2014.81 · DOI · Paper page
  8. 10.1007/s11263-013-0620-5 · DOI · Paper page
  9. graves, 2009, Offline handwriting recognition with multidimensional recurrent neural networks, NIPS
  10. 10.1109/ICCV.2011.6126343 · DOI · Paper page
  11. he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, ECCV
  12. hoiem, 2012, Diagnosing error in object detectors, ECCV
  13. jia, 2014, Caffe Convolutional Architecture for Fast Feature Embedding
  14. karpathy, 2015, Visualizing and understanding recurrent networks
  15. parikh, 2011, Exploring tiny images: The roles of appearance and contextual information for machine and human object recognition, PAMI
  16. chatfield, 2014, Return of the devil in the details: Delving deep into convolutional nets, BMVC
  17. 10.1023/A:1011139631724 · DOI · Paper page
  18. 10.1109/CVPR.2015.7298977 · DOI · Paper page
  19. 10.1109/CVPR.2009.5206532 · DOI · Paper page
  20. pinheiro, 2015, Learning to segment object candidates, NIPS
  21. 10.3115/v1/W14-4012 · DOI · Paper page
  22. gidaris, 2015, Object detection via a multiregion & semantic segmentation-aware CNN model, ICCV
  23. behnke, 2003, Hierarchical Neural Networks for Image Interpretation, 10.1007/b11963 · DOI · Paper page
  24. 10.1007/BF00318371 · DOI · Paper page
  25. 10.1109/CVPR.2016.98 · DOI · Paper page
  26. visin, 2015, Renet A recurrent neural network based alternative to convolutional networks
  27. lin, 2014, Microsoft coco Common objects in context
  28. le, 2015, A simple way to initialize recurrent networks of rectified linear units
  29. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  30. zitnick, 2014, Edge boxes: Locating object proposals from edges, ECCV
  31. liu, 2015, Parsenet Looking wider to see better

Cited by

See all 1,292

Metadata

Authors
Bell, S., Zitnick, C. L., Bala, K., & Girshick, R.
Venue
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2016-06
Pages
2874-2883
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2016.314
OpenAlex
W2288122362
Cited by
1,292
References
14
FWCI
62.96
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks. https://app.cochat.ai/papers/10.1109/cvpr.2016.314
The paper
Bell, S., Zitnick, C. L., Bala, K., & Girshick, R. (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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.