Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 177

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks

Ouyang, Wanli, Zeng, Xingyu, Wang, Xiaogang, Qiu, Shi, Luo, Ping, Tian, Yonglong, Li, Hongsheng, Yang, Shuo, Wang, Zhe, Li, Hongyang, Wang, Kun, Yan, Junjie, Loy, Chen-Change, Tang, Xiaoou · 2017 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [16], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provides a global view for people to understand the deep learning object detection pipeline.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/tpami.2016.2587642

Cites

12 of 12 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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 12 references

Research works printed but not linked: 70

  1. 10.1109/ICCV.2013.134 · DOI
  2. 10.1109/CVPR.2011.5995711 · DOI · Paper page
  3. desai, 2012, Detecting actions, poses, and objects with relational phraselets, Proc 12th Eur Conf Comput Vis, 158
  4. 10.1145/2647868.2654889 · DOI · Paper page
  5. 10.1109/CVPR.2014.244 · DOI · Paper page
  6. 10.1109/CVPR.2015.7298641 · DOI · Paper page
  7. 10.1109/CVPR.2013.446 · DOI · Paper page
  8. 10.1109/CVPR.2013.417 · DOI · Paper page
  9. 10.1109/CVPR.2013.414 · DOI
  10. gong, 2014, Multi-scale orderless pooling of deep convolutional activation features, European Conf Comput Vis, 392
  11. zou, 2014, Generic object detection with dense neural patterns and regionlets, Proc British Mach Vis Conf
  12. 10.1109/CVPR.2014.120 · DOI · Paper page
  13. 10.1109/CVPR.2014.299 · DOI · Paper page
  14. 10.1109/ICCV.2013.22 · DOI
  15. zeng, 2014, Deep learning of scene-specific classifier for pedestrian detection, Proc 13th Eur Conf Comput Vis, 472
  16. 10.1109/CVPR.2009.5206532 · DOI · Paper page
  17. 10.1109/CVPR.2010.5539905 · DOI
  18. heitz, 2008, Learning spatial context: Using stuff to find things, Proc 10th Eur Conf Comput Vis Part I, 30
  19. 10.1007/s11263-006-0027-7 · DOI · Paper page
  20. 10.1109/CVPR.2014.256 · DOI
  21. yan, 2012, Multi-pedestrian detection in crowded scenes: A global view, Proc IEEE Conf Comput Vis Pattern Recog, 3124
  22. 10.1109/CVPR.2011.5995741 · DOI · Paper page
  23. 10.1109/ICCV.2009.5459256 · DOI · Paper page
  24. park, 2010, Multiresolution models for object detection, Proc 11th Eur Conf Comput Vis, 241
  25. 10.1109/CVPR.2011.5995330 · DOI · Paper page
  26. 10.1109/CVPR.2010.5540235 · DOI · Paper page
  27. 10.1109/CVPR.2012.6248095 · DOI
  28. 10.1007/s11263-009-0275-4 · DOI · Paper page
  29. 10.1109/CVPR.2014.81 · DOI · Paper page
  30. zeiler, 2014, Visualizing and understanding convolutional neural networks, European Conf Comput Vis, 818
  31. 10.1109/CVPR.2015.7298854 · DOI · Paper page
  32. 10.1109/CVPR.2016.335 · DOI · Paper page
  33. 10.1109/TPAMI.2014.2377734 · DOI
  34. 10.1109/ICCV.2009.5459303 · DOI · Paper page
  35. 10.1109/CVPR.2014.320 · DOI · Paper page
  36. lenc, 2015, R-CNN minus R, arXiv 1506 06981
  37. 10.1109/CVPR.2010.5540223 · DOI
  38. ding, 2012, Contextual boost for pedestrian detection, Proc IEEE Conf Comput Vis Pattern Recog, 2895
  39. 10.1109/ICCV.2013.257 · DOI · Paper page
  40. 10.1109/TCSVT.2016.2629621 · DOI
  41. 10.1007/s11263-016-0890-9 · DOI
  42. 10.1109/CVPR.2016.100 · DOI · Paper page
  43. 10.1109/ICCV.2015.220 · DOI
  44. 10.1109/CVPRW.2014.131 · DOI · Paper page
  45. 10.1109/ICCV.2013.188 · DOI · Paper page
  46. zhang, 2014, Part-based R-CNNs for fine-grained category detection, Proc 13th Eur Conf Comput Vis, 834
  47. zhu, 2010, Latent hierarchical structural learning for object detection, Proc IEEE Conf Comput Vis Pattern Recog, 1062
  48. 10.1023/B:VISI.0000042934.15159.49 · DOI · Paper page
  49. hoiem, 2012, Diagnosing error in object detectors, Proc 12th Eur Conf Comput Vis, 340
  50. 10.1109/TPAMI.2012.261 · DOI · Paper page
  51. van de sande, 2014, Fisher and VLAD with flair, Proc IEEE Conf Comput Vis Pattern Recog, 2377
  52. 10.1109/CVPR.2013.411 · DOI · Paper page
  53. yan, 2014, Deeper vision and deep insight solutions, Proc Eur Conf Comput Vis Workshop ImageNet Large Scale Visual Recog Challenge
  54. chatfield, 2014, Return of the devil in the details: Delving deep into convolutional nets, Proc British Mach Vis Conf
  55. lin, 2014, Microsoft COCO: Common objects in context, Proc 13th Eur Conf Comput Vis, 740
  56. 10.1109/ICCV.2013.10 · DOI · Paper page
  57. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  58. 10.1007/s11263-015-0816-y · DOI · Paper page
  59. simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv 1409 1556
  60. zhou, 2014, Learning deep features for scene recognition using places database, Proc Conf Adv Neural Inf Process Syst, 487
  61. lin, 2013, Network in network, arXiv 1312 4400
  62. zhou, 2015, Object detectors emerge in deep scene CNNs, Proc Int Conf Learn Represent
  63. 10.1109/CVPR.2015.7299146 · DOI
  64. 10.1109/CVPR.2015.7298621 · DOI · Paper page
  65. 10.1109/ICCV.2015.169 · DOI · Paper page
  66. 10.1109/ICCV.2015.18 · DOI · Paper page
  67. luo, 2013, Pedestrian parsing via deep decompositional neural network, Proc IEEE Int Conf Comput Vis, 2648
  68. 10.1109/ICCV.2013.356 · DOI
  69. 10.1109/CVPR.2015.7298731 · DOI · Paper page
  70. luo, 2012, Hierarchical face parsing via deep learning, Proc IEEE Conf Comput Vis Pattern Recog, 2480

Cited by

Metadata

Authors
Ouyang, W., Zeng, X., Wang, X., Qiu, S., Luo, P., Tian, Y., Li, H., Yang, S., Wang, Z., Li, H., Wang, K., Yan, J., Loy, C.-C., & Tang, X.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2017-07-01
Volume
39
Issue
7
Pages
1320-1334
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
OpenAlex
W2528333963
Cited by
177
References
12
FWCI
10.27
Type
journal article
Language
en
Open access
closed
Funders
  • General Research Fund
  • Research Grants Council of Hong Kong (CUHK14206114, CUHK14205615, CUHK14207814, CUHK417011, CUHK14203015)

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

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.