Skip to main content

2018 | OriginalPaper | Buchkapitel

Context Refinement for Object Detection

verfasst von : Zhe Chen, Shaoli Huang, Dacheng Tao

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Current two-stage object detectors, which consists of a region proposal stage and a refinement stage, may produce unreliable results due to ill-localized proposed regions. To address this problem, we propose a context refinement algorithm that explores rich contextual information to better refine each proposed region. In particular, we first identify neighboring regions that may contain useful contexts and then perform refinement based on the extracted and unified contextual information. In practice, our method effectively improves the quality of the final detection results as well as region proposals. Empirical studies show that context refinement yields substantial and consistent improvements over different baseline detectors. Moreover, the proposed algorithm brings around 3% performance gain on PASCAL VOC benchmark and around 6% gain on MS COCO benchmark respectively.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Bell, S., Lawrence Zitnick, C., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: CVPR, pp. 2874–2883 (2016) Bell, S., Lawrence Zitnick, C., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: CVPR, pp. 2874–2883 (2016)
2.
Zurück zum Zitat Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS-improving object detection with one line of code. In: ICCV (2017) Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS-improving object detection with one line of code. In: ICCV (2017)
3.
4.
Zurück zum Zitat Chen, X., Gupta, A.: Spatial memory for context reasoning in object detection. In: ICCV (2017) Chen, X., Gupta, A.: Spatial memory for context reasoning in object detection. In: ICCV (2017)
6.
Zurück zum Zitat Chen, Z., Hong, Z., Tao, D.: An experimental survey on correlation filter-based tracking (2015). arXiv preprint: arXiv:1509.05520 Chen, Z., Hong, Z., Tao, D.: An experimental survey on correlation filter-based tracking (2015). arXiv preprint: arXiv:​1509.​05520
7.
Zurück zum Zitat Chen, Z., You, X., Zhong, B., Li, J., Tao, D.: Dynamically modulated mask sparse tracking. IEEE Trans. Cybern. 47(11), 3706–3718 (2017)CrossRef Chen, Z., You, X., Zhong, B., Li, J., Tao, D.: Dynamically modulated mask sparse tracking. IEEE Trans. Cybern. 47(11), 3706–3718 (2017)CrossRef
8.
Zurück zum Zitat Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379–387 (2016) Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379–387 (2016)
9.
Zurück zum Zitat Dai, J., et al.: Deformable convolutional networks (2017) Dai, J., et al.: Deformable convolutional networks (2017)
10.
Zurück zum Zitat Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A.A., Hebert, M.: An empirical study of context in object detection. In: CVPR, pp. 1271–1278. IEEE (2009) Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A.A., Hebert, M.: An empirical study of context in object detection. In: CVPR, pp. 1271–1278. IEEE (2009)
11.
Zurück zum Zitat Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2010)CrossRef Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2010)CrossRef
12.
Zurück zum Zitat Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: ICCV, pp. 1134–1142 (2015) Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: ICCV, pp. 1134–1142 (2015)
13.
Zurück zum Zitat Gidaris, S., Komodakis, N.: Attend refine repeat: active box proposal generation via in-out localization. In: BMVC (2016) Gidaris, S., Komodakis, N.: Attend refine repeat: active box proposal generation via in-out localization. In: BMVC (2016)
14.
Zurück zum Zitat Gidaris, S., Komodakis, N.: Locnet: improving localization accuracy for object detection. In: CVPR, pp. 789–798 (2016) Gidaris, S., Komodakis, N.: Locnet: improving localization accuracy for object detection. In: CVPR, pp. 789–798 (2016)
15.
Zurück zum Zitat Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440–1448 (2015) Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440–1448 (2015)
16.
Zurück zum Zitat He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017) He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)
17.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
18.
Zurück zum Zitat Hong, Z., Chen, Z., Wang, C., Mei, X., Prokhorov, D., Tao, D.: Multi-store tracker (muster): a cognitive psychology inspired approach to object tracking. In: CVPR, pp. 749–758 (2015) Hong, Z., Chen, Z., Wang, C., Mei, X., Prokhorov, D., Tao, D.: Multi-store tracker (muster): a cognitive psychology inspired approach to object tracking. In: CVPR, pp. 749–758 (2015)
19.
Zurück zum Zitat Hosang, J., Benenson, R., Schiele, B.: Learning non-maximum suppression. In: CVPR (2017) Hosang, J., Benenson, R., Schiele, B.: Learning non-maximum suppression. In: CVPR (2017)
20.
Zurück zum Zitat Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017) Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)
21.
Zurück zum Zitat Kong, T., Yao, A., Chen, Y., Sun, F.: Hypernet: towards accurate region proposal generation and joint object detection. In: CVPR, pp. 845–853 (2016) Kong, T., Yao, A., Chen, Y., Sun, F.: Hypernet: towards accurate region proposal generation and joint object detection. In: CVPR, pp. 845–853 (2016)
22.
Zurück zum Zitat Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017) Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)
25.
Zurück zum Zitat Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: CVPR, pp. 891–898 (2014) Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: CVPR, pp. 891–898 (2014)
26.
Zurück zum Zitat Ouyang, W., Wang, K., Zhu, X., Wang, X.: Learning chained deep features and classifiers for cascade in object detection. In: ICCV (2017) Ouyang, W., Wang, K., Zhu, X., Wang, X.: Learning chained deep features and classifiers for cascade in object detection. In: ICCV (2017)
27.
Zurück zum Zitat Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779–788 (2016) Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779–788 (2016)
28.
Zurück zum Zitat Ren, J., et al.: Accurate single stage detector using recurrent rolling convolution. In: CVPR (2017) Ren, J., et al.: Accurate single stage detector using recurrent rolling convolution. In: CVPR (2017)
29.
Zurück zum Zitat Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015) Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)
30.
Zurück zum Zitat Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: CVPR, pp. 1919–1927 (2017) Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: CVPR, pp. 1919–1927 (2017)
31.
Zurück zum Zitat Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: top-down modulation for object detection (2016). arXiv preprint: arXiv:1612.06851 Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: top-down modulation for object detection (2016). arXiv preprint: arXiv:​1612.​06851
32.
Zurück zum Zitat Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015) Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015)
33.
Zurück zum Zitat Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017) Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017)
34.
Zurück zum Zitat Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154–171 (2013)CrossRef Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154–171 (2013)CrossRef
35.
Zurück zum Zitat Yu, R.R., Chen, X.S., Morariu, V.I., Davis, L.S., Redmond, W.: The role of context selection in object detection. T-PAMI 32(9), 1627–1645 (2010)CrossRef Yu, R.R., Chen, X.S., Morariu, V.I., Davis, L.S., Redmond, W.: The role of context selection in object detection. T-PAMI 32(9), 1627–1645 (2010)CrossRef
37.
Zurück zum Zitat Zeng, X., et al.: Crafting GBD-net for object detection. T-PAMI 40, 2109–2123 (2017)CrossRef Zeng, X., et al.: Crafting GBD-net for object detection. T-PAMI 40, 2109–2123 (2017)CrossRef
Metadaten
Titel
Context Refinement for Object Detection
verfasst von
Zhe Chen
Shaoli Huang
Dacheng Tao
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-01237-3_5

Premium Partner