Abstract
We propose a weakly supervised approach to semantic segmentation using bounding box annotations. Bounding boxes are treated as noisy labels for the foreground objects. We predict a per-class attention map that saliently guides the per-pixel cross entropy loss to focus on foreground pixels and refines the segmentation boundaries. This avoids propagating erroneous gradients due to incorrect foreground labels on the background. Additionally, we learn pixel embeddings to simultaneously optimize for high intra-class feature affinity while increasing discrimination between features across different classes. Our method, Box2Seg, achieves state-of-the-art segmentation accuracy on PASCAL VOC 2012 by significantly improving the mIOU metric by \(2.1\%\) compared to previous weakly supervised approaches. Our weakly supervised approach is comparable to the recent fully supervised methods when fine-tuned with limited amount of pixel-level annotations. Qualitative results and ablation studies show the benefit of different loss terms on the overall performance.
V. Kulharia, S.Chandra — Equally Contributed.
V. Kulharia was an intern at Amazon Lab126.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahn, J., Cho, S., Kwak, S.: Weakly supervised learning of instance segmentation with inter-pixel relations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2209–2218 (2019)
Ahn, J., Kwak, S.: Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Arandjelović, R., Zisserman, A.: Object discovery with a copy-pasting gan. arXiv preprint arXiv:1905.11369 (2019)
Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What’s the point: semantic segmentation with point supervision. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 549–565. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_34
Chandra, S., Usunier, N., Kokkinos, I.: Dense and low-rank gaussian crfs using deep embeddings. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5103–5112 (2017)
Chaudhry, A., Dokania, P.K., Torr, P.H.: Discovering class-specific pixels for weakly-supervised semantic segmentation. In: British Machine Vision Conference (BMVC) (2017)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 (2014)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arXiv:1606.00915 (2016)
Chen, L., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. CoRR abs/1706.05587 (2017). http://arxiv.org/abs/1706.05587
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European Conference on Computer Vision (ECCV), pp. 801–818 (2018)
Dai, J., He, K., Sun, J.: Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: International Conference on Computer Vision (ICCV), 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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)
Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. (IJCV) 88(2), 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4
Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: International Conference on Computer Vision (ICCV) (2011)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: International Conference on Computer Vision (ICCV) (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Hou, Q., Massiceti, D., Dokania, P.K., Wei, Y., Cheng, M.M., Torr, P.H.S.: Bottom-up top-down cues for weakly-supervised semantic segmentation. In: Pelillo, M., Hancock, E. (eds.) EMMCVPR 2017. LNCS, vol. 10746, pp. 263–277. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78199-0_18
Hsu, K.J., Lin, Y.Y., Chuang, Y.Y.: Deepco3: deep instance co-segmentation by co-peak search and co-saliency detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Hu, R., Dollár, P., He, K., Darrell, T., Girshick, R.: Learning to segment every thing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4233–4241 (2018)
Huang, Z., Wang, X., Wang, J., Liu, W., Wang, J.: Weakly-supervised semantic segmentation network with deep seeded region growing. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7014–7023 (2018)
Hung, W.C., Tsai, Y.H., Liou, Y.T., Lin, Y.Y., Yang, M.H.: Adversarial learning for semi-supervised semantic segmentation. In: British Machine Vision Conference (BMVC) (2018)
Ke, T.W., Hwang, J.J., Liu, Z., Yu, S.X.: Adaptive affinity fields for semantic segmentation. In: European Conference on Computer Vision (ECCV) (2018)
Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Simple does it: weakly supervised instance and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 876–885 (2017)
Krähenbühl, P., Koltun, V.: Efficient inference in fully connected crfs with gaussian edge potentials. In: Neural Information Processing Systems (NIPS) (2011)
Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018)
Kwak, S., Hong, S., Han, B.: Weakly supervised semantic segmentation using superpixel pooling network. In: AAAI Conference on Artificial Intelligence (2017)
Lee, J., Kim, E., Lee, S., Lee, J., Yoon, S.: Frame-to-frame aggregation of active regions in web videos for weakly supervised semantic segmentation. In: International Conference on Computer Vision (ICCV), October 2019
Li, Q., Arnab, A., Torr, P.H.: Weakly-and semi-supervised panoptic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV 18), pp. 102–118 (2018)
Lin, D., Dai, J., Jia, J., He, K., Sun, J.: Scribblesup: scribble-supervised convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3159–3167 (2016)
Lin, T.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, S., De Mello, S., Gu, J., Zhong, G., Yang, M.H., Kautz, J.: Learning affinity via spatial propagation networks. In: Neural Information Processing Systems (NIPS) (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440 (2015)
Maire, M., Narihira, T., Yu, S.X.: Affinity cnn: learning pixel-centric pairwise relations for figure/ground embedding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Min, S., Chen, X., Zha, Z.J., Wu, F., Zhang, Y.: A two-stream mutual attention network for semi-supervised biomedical segmentation with noisy labels (2018)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: arXiv preprint arXiv:1505.04366 (2015)
Papadopoulos, D.P., Uijlings, J.R., Keller, F., Ferrari, V.: Extreme clicking for efficient object annotation. In: IEEE International Conference on Computer Vision (CVPR), pp. 4930–4939 (2017)
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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1742–1750 (2015)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Petit, O., Thome, N., Charnoz, A., Hostettler, A., Soler, L.: Handling missing annotations for semantic segmentation with deep convNets. In: Stoyanov, D., et al. (eds.) DLMIA/ML-CDS -2018. LNCS, vol. 11045, pp. 20–28. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00889-5_3
Pont-Tuset, J., Arbelaez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(1), 128–140 (2016)
Rajchl, M., et al.: Deepcut: object segmentation from bounding box annotations using convolutional neural networks. IEEE Trans. Med. Imaging 36(2), 674–683 (2016)
Redondo-Cabrera, C., Baptista-Ríos, M., López-Sastre, R.J.: Learning to exploit the prior network knowledge for weakly supervised semantic segmentation. IEEE Trans. Image Process. 28(7), 3649–3661 (2019)
Richter, S.R., Hayder, Z., Koltun, V.: Playing for benchmarks. In: International Conference on Computer Vision (ICCV) (2017)
Rother, C., Kolmogorov, V., Blake, A.: Grabcut: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309–314 (2004)
Singh, B., Najibi, M., Davis, L.S.: SNIPER: efficient multi-scale training. In: Neural Information Processing Systems (NIPS) (2018)
Song, C., Huang, Y., Ouyang, W., Wang, L.: Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3136–3145 (2019)
Tang, M., Djelouah, A., Perazzi, F., Boykov, Y., Schroers, C.: Normalized cut loss for weakly-supervised cnn segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1818–1827 (2018)
Tang, M., Perazzi, F., Djelouah, A., Ben Ayed, I., Schroers, C., Boykov, Y.: On regularized losses for weakly-supervised cnn segmentation. In: European Conference on Computer Vision (ECCV), pp. 507–522 (2018)
Wang, B., et al.: Boundary perception guidance: a scribble-supervised semantic segmentation approach. In: International Joint Conference on Artificial Intelligence (IJCAI) (2019)
Wang, X., You, S., Li, X., Ma, H.: Weakly-supervised semantic segmentation by iteratively mining common object features. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1354–1362 (2018)
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: European Conference on Computer Vision (ECCV), pp. 418–434 (2018)
Zeng, Y., Zhuge, Y., Lu, H., Zhang, L.: Joint learning of saliency detection and weakly supervised semantic segmentation. Int. Conf. Comput. Vis. (ICCV) 3(11), 12 (2019)
Zhang, H., et al.: Context encoding for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Zhang, H., Zhang, H., Wang, C., Xie, J.: Co-occurrent features in semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhao, X., Liang, S., Wei, Y.: Pseudo mask augmented object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4061–4070 (2018)
Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: International Conference on Computer Vision (ICCV) (2015)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929 (2016)
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Zhu, Y., Zhou, Y., Xu, H., Ye, Q., Doermann, D., Jiao, J.: Learning instance activation maps for weakly supervised instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3116–3125 (2019)
Acknowledgements
V. Kulharia worked as an intern at Amazon Lab126 and continued this work at Oxford University. V Kulharia’s DPhil is funded by the Toyota Research Institute grant.
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
Kulharia, V., Chandra, S., Agrawal, A., Torr, P., Tyagi, A. (2020). Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12372. Springer, Cham. https://doi.org/10.1007/978-3-030-58583-9_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-58583-9_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58582-2
Online ISBN: 978-3-030-58583-9
eBook Packages: Computer ScienceComputer Science (R0)