Abstract
Fully supervised semantic segmentation is highly successful, but obtaining dense ground truth is expensive. Thus there is an increasing interest in weakly supervised approaches. We propose a new weakly supervised method for training CNNs to segment an object of a single class of interest. Instead of ground truth, we guide training with a regularized loss function. Regularized loss models prior knowledge about the likely object shape properties and thus guides segmentation towards the more plausible shapes. Training CNNs with regularized loss is difficult. We develop an annealing strategy that is crucial for successful training. The advantage of our method is simplicity: we use standard CNN architectures and intuitive and computationally efficient loss function. Furthermore, we apply the same loss function for any task/dataset, without any tailoring. We first evaluate our approach for salient object segmentation and co-segmentation. These tasks naturally involve one object class of interest. In some cases, our results are only a few points of standard performance measure behind those obtained training the same CNN with full supervision, and state-of-the art results in weakly supervised setting. Then we adapt our approach to weakly supervised multi-class semantic segmentation and obtain state-of-the-art results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
In the context of CNNs, regularization is a term often used to refer to norm regularization on network weights [12], or other techniques to prevent overfitting. In this work, regularized loss refers to the loss function on the output of CNN.
- 2.
- 3.
Note that our volumetric prior is actually defined on batches of images. However for the simplicity of notation, we write \( L_{v}(\textit{\textbf{x}})\) in this equation
References
Ahn, J., Kwak, S.: Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 4981–4990 (2018)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222–1239 (2001)
Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: 9th IEEE International Conference on Computer Vision (ICCV 2003), 14–17 October 2003, Nice, France, pp. 26–33 (2003)
Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: International Conference on Learning Research (2015)
Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49
Dai, J., He, K., Sun, J.: Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: International Conference on Computer Vision, pp. 1635–1643 (2015)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303–338 (2010)
Faktor, A., Irani, M.: Co-segmentation by composition. In: International Conference on Computer Vision, pp. 1297–1304 (2013)
Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. (2013). (in press)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Gorelick, L., Veksler, O., Boykov, Y., Nieuwenhuis, C.: Convexity shape prior for segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 675–690. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_44
Hsu, K.J., Lin, Y.Y., Chuang, Y.Y.: Co-attention CNNs for unsupervised object co-segmentation. In: IJCAI, pp. 748–756 (2018)
Khoreva, A., Benenson, R., Hosang, J.H., Hein, M., Schiele, B.: Simple does it: weakly supervised instance and semantic segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 1665–1674 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kirkpatrick, S., Gelatt, C., Vecchi, M.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)
Kolesnikov, A., Lampert, C.H.: Seed, expand and constrain: three principles for weakly-supervised image segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 695–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_42
Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: Neural Information Processing Systems, pp. 109–117 (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems (2012)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields. In: International Conference on Machine Learning (2001)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Lee, J., Kim, E., Lee, S., Lee, J., Yoon, S.: Ficklenet: weakly and semi-supervised semantic image segmentation using stochastic inference. In: Conference on Computer Vision and Pattern Recognition, pp. 5267–5276 (2019)
Li, B., Sun, Z., Li, Q., Wu, Y., Hu, A.: Group-wise deep object co-segmentation with co-attention recurrent neural network. In: International Conference on Computer Vision, October 2019
Li, S.: Markov Random Field Modeling in Computer Vision. Springer, London (1995). https://doi.org/10.1007/978-4-431-66933-3
Lin, D., Dai, J., Jia, J., He, K., Sun, J.: Scribblesup: scribble-supervised convolutional networks for semantic segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 3159–3167 (2016)
Liu, T., Sun, J., Zheng, N.N., Tang, X., Shum, H.Y.: Learning to detect a salient object. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2007)
Nguyen, T., et al.: Deepusps: deep robust unsupervised saliency prediction via self-supervision. In: Advances in Neural Information Processing Systems, pp. 204–214 (2019)
Papandreou, G., Chen, L.C., Murphy, K.P., Yuille, A.L.: Weakly and semi supervised learning of a deep convolutional network for semantic image segmentation. In: International Conference on Computer Vision, pp. 1742–1750 (2015)
Pinheiro, P.H.O., Collobert, R.: From image-level to pixel-level labeling with convolutional networks. In: Conference on Computer Vision and Pattern Recognition, pp. 1713–1721 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention, pp. 234–241 (2015)
Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 993–1000 (2006)
Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: International Conference on Computer Vision, pp. 618–626 (2017)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017)
Shen, T., Lin, G., Liu, L., Shen, C., Reid, I.D.: Weakly supervised semantic segmentation based on co-segmentation. In: BMVC (2017)
Shen, T., Lin, G., Shen, C., Reid, I.: Bootstrapping the performance of webly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1363–1371 (2018)
Shimoda, W., Yanai, K.: Self-supervised difference detection for weakly-supervised semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5208–5217 (2019)
Takikawa, T., Acuna, D., Jampani, V., Fidler, S.: Gated-SCNN: gated shape CNNs for semantic segmentation. In: International Conference on Computer Vision (2019)
Tang, M., Djelouah, A., Perazzi, F., Boykov, Y., Schroers, C.: Normalized cut loss for weakly-supervised CNN segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 1818–1827 (2018)
Tang, M., Perazzi, F., Djelouah, A., Ayed, I.B., Schroers, C., Boykov, Y.: On regularized losses for weakly-supervised CNN segmentation. In: European Conference on Computer Vision. pp. 524–540 (2018)
Vedaldi, A.: Cats and dogs. In: Conference on Computer Vision and Pattern Recognition (2012)
Veksler, O.: Efficient graph cut optimization for full CRFs with quantized edges. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 1005–1012 (2020)
Vernaza, P., Chandraker, M.: Learning random-walk label propagation for weakly-supervised semantic segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 2953–2961 (2017)
Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)
Vogiatzis, G., Torr, P., Cipolla, R.: Multi-view stereo via volumetric graph-cuts. In: Conference on Computer Vision and Pattern Recognition, pp. II: 391–398 (2005)
Wang, X., You, S., Li, X., Ma, H.: Weakly-supervised semantic segmentation by iteratively mining common object features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1354–1362 (2018)
Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., Huang, T.S.: Revisiting dilated convolution: a simple approach for weakly-and semi-supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7268–7277 (2018)
Wu, H., Zhang, J., Huang, K., Liang, K., Yu, Y.: Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation. CoRR abs/1903.11816 (2019)
Xie, S., Girshick, R.B., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Conference on Computer Vision and Pattern Recognition, pp. 5987–5995 (2017)
Xu, J., Schwing, A.G., Urtasun, R.: Learning to segment under various forms of weak supervision. In: Conference on Computer Vision and Pattern Recognition, pp. 3781–3790 (2015)
Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection. In: Conference on Computer Vision and Pattern Recognition, pp. 1155–1162. IEEE (2013)
Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: Conference on Computer Vision and Pattern Recognition, pp. 3166–3173. IEEE (2013)
Zeng, Y., Zhuge, Y., Lu, H., Zhang, L.: Joint learning of saliency detection and weakly supervised semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7223–7233 (2019)
Zhang, D., Han, J., Zhang, Y.: Supervision by fusion: Towards unsupervised learning of deep salient object detector. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4048–4056 (2017)
Zhang, J., Zhang, T., Dai, Y., Harandi, M., Hartley, R.: Deep unsupervised saliency detection: A multiple noisy labeling perspective. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9029–9038 (2018)
Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.: Conditional random fields as recurrent neural networks. In: International Conference on Computer Vision, pp. 1529–1537 (2015)
Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Veksler, O. (2020). Regularized Loss for Weakly Supervised Single Class Semantic Segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12374. Springer, Cham. https://doi.org/10.1007/978-3-030-58526-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-58526-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58525-9
Online ISBN: 978-3-030-58526-6
eBook Packages: Computer ScienceComputer Science (R0)