Skip to main content
SpringerLink
Log in
Book cover

European Conference on Computer Vision

ECCV 2020: Computer Vision – ECCV 2020 Workshops pp 245–260Cite as

Two-Stage Training for Improved Classification of Poorly Localized Object Images

  • Conference paper
  • First Online:

  • 1818 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12539))

Abstract

State-of-the-art object classifiers finetuned from a pretrained (e.g. from ImageNet) model on a domain-specific dataset can accurately classify well-localized object images. However, such classifiers often fail on poorly localized images (images with lots of context, heavily occluded/partially visible, and off-centered objects). In this paper, we propose a two-stage training scheme to improve the classification of such noisy detections, often produced by low-compute algorithms such as motion based background removal techniques that run on the edge. The proposed two-stage training pipeline first trains a classifier from scratch with extreme image augmentation, followed by finetuning in the second stage. The first stage incorporates a lot of contextual information around the objects, given access to the corresponding full images. This stage works very well for classification of poorly localized input images, but generates a lot of false positives by classifying non-object images as objects. To reduce the false positives, a second training is done on the tight ground-truth bounding boxes (as done traditionally) by using the trained model in the first stage as the initial model and very slowly adjusting its weights during the training. To demonstrate the efficacy of our approach, we curated a new classification dataset for poorly localized images - noisy PASCAL VOC 2007 test dataset. Using this dataset, we show that the proposed two-stage training scheme can significantly improve the accuracy of the trained classifier on both well-localized and poorly-localized object images.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    https://github.com/sravbond/voc2007noisy.

  2. 2.

    https://github.com/sravbond/voc2007noisy.

  3. 3.

    https://developer.nvidia.com/digits.

  4. 4.

    https://docs.nvidia.com/deeplearning/frameworks/caffe-user-guide/index.html.

References

  1. Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection (2020)

    Google Scholar 

  2. Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment (2019)

    Google Scholar 

  3. Chen, P., Liu, S., Zhao, H., Jia, J.: Gridmask data augmentation (2020)

    Google Scholar 

  4. Chin, T., Ding, R., Zhang, C., Marculescu, D.: Legr: filter pruning via learned global ranking. CoRR abs/1904.12368 (2019). http://arxiv.org/abs/1904.12368

  5. Dai, X., et al.: Fbnetv3: joint architecture-recipe search using neural acquisition function (2020)

    Google Scholar 

  6. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009)

    Google Scholar 

  7. Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. CoRR abs/1708.04552 (2017). http://arxiv.org/abs/1708.04552

  8. Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98–136 (2015)

    Article  Google Scholar 

  9. Freund, Y., Schapire, R.E.: A decision theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P.M.B. (ed.) Second European Conference on Computational Learning Theory (EuroCOLT-95), pp. 23–37 (1995). citeseer.nj.nec.com/freund95decisiontheoretic.html

  10. He, Y., Han, S.: AMC: automated deep compression and acceleration with reinforcement learning. CoRR abs/1802.03494 (2018). http://arxiv.org/abs/1802.03494

  11. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)

    Google Scholar 

  12. Howard, A., et al.: Searching for mobilenetv3. CoRR abs/1905.02244 (2019). http://arxiv.org/abs/1905.02244

  13. Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017). http://arxiv.org/abs/1704.04861

  14. Huang, G., Liu, S., van der Maaten, L., Weinberger, K.Q.: Condensenet: an efficient densenet using learned group convolutions. CoRR abs/1711.09224 (2017). http://arxiv.org/abs/1711.09224

  15. Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and<1mb model size. CoRR abs/1602.07360 (2016), http://arxiv.org/abs/1602.07360

  16. Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper. CoRR abs/1806.08342 (2018), http://arxiv.org/abs/1806.08342

  17. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection (2017)

    Google Scholar 

  18. Liu, C., et al.: Progressive neural architecture search. CoRR abs/1712.00559 (2017), http://arxiv.org/abs/1712.00559

  19. Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. CoRR abs/1806.09055 (2018), http://arxiv.org/abs/1806.09055

  20. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector (2015), http://arxiv.org/abs/1512.02325, cite arxiv:1512.02325Comment: ECCV 2016

  21. Polino, A., Pascanu, R., Alistarh, D.: Model compression via distillation and quantization. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=S1XolQbRW

  22. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. CoRR abs/1802.01548 (2018), http://arxiv.org/abs/1802.01548

  23. Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR abs/1612.08242 (2016), http://arxiv.org/abs/1612.08242

  24. Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. CoRR abs/1801.04381 (2018), http://arxiv.org/abs/1801.04381

  25. Shetty, R., Schiele, B., Fritz, M.: Not using the car to see the sidewalk: quantifying and controlling the effects of context in classification and segmentation. CoRR abs/1812.06707 (2018), http://arxiv.org/abs/1812.06707

  26. Singh, K.K., Yu, H., Sarmasi, A., Pradeep, G., Lee, Y.J.: Hide-and-seek: a data augmentation technique for weakly-supervised localization and beyond. CoRR abs/1811.02545 (2018), http://arxiv.org/abs/1811.02545

  27. Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2019)

    Google Scholar 

  28. Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. CoRR abs/1905.11946 (2019), http://arxiv.org/abs/1905.11946

  29. Touvron, H., Vedaldi, A., Douze, M., Jégou, H.: Fixing the train-test resolution discrepancy: Fixefficientnet (2020)

    Google Scholar 

  30. Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade of simple features. In: CVPR (1), pp. 511–518. IEEE Computer Society (2001)

    Google Scholar 

  31. Wan, A., et al.: Fbnetv2: differentiable neural architecture search for spatial and channel dimensions (2020)

    Google Scholar 

  32. Wu, B., et al.: Fbnet: hardware-aware efficient convnet design via differentiable neural architecture search. CoRR abs/1812.03443 (2018), http://arxiv.org/abs/1812.03443

  33. Wu, B., et al.: Shift: a zero flop, zero parameter alternative to spatial convolutions. CoRR abs/1711.08141 (2017), http://arxiv.org/abs/1711.08141

  34. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. CoRR abs/1905.04899 (2019), http://arxiv.org/abs/1905.04899

  35. Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. CoRR abs/1710.09412 (2017), http://arxiv.org/abs/1710.09412

  36. Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. CoRR abs/1707.01083 (2017), http://arxiv.org/abs/1707.01083

  37. Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. CoRR abs/1708.04896 (2017), http://arxiv.org/abs/1708.04896

  38. Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. CoRR abs/1611.01578 (2016), http://arxiv.org/abs/1611.01578

  39. Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. CoRR abs/1707.07012 (2017), http://arxiv.org/abs/1707.07012

Download references

Author information

Authors and Affiliations

  1. Object Video Labs, LLC, McLean, USA

    Sravanthi Bondugula, Gang Qian & Allison Beach

Authors
  1. Sravanthi Bondugula
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gang Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Allison Beach
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sravanthi Bondugula .

Editor information

Editors and Affiliations

  1. University of Clermont Auvergne, Clermont Ferrand, France

    Adrien Bartoli

  2. Università degli Studi di Udine, Udine, Italy

    Andrea Fusiello

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bondugula, S., Qian, G., Beach, A. (2020). Two-Stage Training for Improved Classification of Poorly Localized Object Images. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12539. Springer, Cham. https://doi.org/10.1007/978-3-030-68238-5_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-68238-5_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-68237-8

  • Online ISBN: 978-3-030-68238-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation