Abstract
Single Positive Multi-Label Learning (SPML) is a method for a scarcely annotated setting, in which each image is assigned only one positive label while the other labels remain unannotated. Most approaches for SPML assume unannotated labels as negatives (“Assumed Negative”, AN). However, with this assumption, some positive labels are inevitably regarded as negative (false negative), resulting in model performance degradation. Therefore, identifying false negatives is the most important with AN assumption. Previous approaches identified false negative labels using the model outputs of assumed negative labels. However, models were trained with noisy negative labels, their outputs were not reliable. Therefore, it is necessary to consider effectively utilizing the most reliable information in SPML for identifying false negative labels. In this paper, we propose the Information Gap-based False Negative LOss REjection (IGNORE) method for SPML. We generate the masked image that all parts are removed except for the discriminative area of the single positive label. It is reasonable that when there is no information of an object in the masked image, the model’s logit for that object is low. Based on this intuition, we identify the false negative labels if they have a significant model’s logit gap between the masked image and the original image. Also, by rejecting false negatives in the model training, we can prevent the model from being biased to false negative labels, and build more reliable models. We evaluate our method on four datasets: Pascal VOC 2012, MS COCO, NUSWIDE, and CUB. Compared to previous state-of-the-art methods in SPML, our method outperforms them on most of the datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Berthelot, D., et al.: ReMixMatch: semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785 (2019)
Beyer, L., Hénaff, O.J., Kolesnikov, A., Zhai, X., Oord, A.: Are we done with ImageNet? arXiv preprint arXiv:2006.07159 (2020)
Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177–5186 (2019)
Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from National University of Singapore. In: Proceedings of the ACM International Conference on Image and Video Retrieval, pp. 1–9 (2009)
Cole, E., Mac Aodha, O., Lorieul, T., Perona, P., Morris, D., Jojic, N.: Multi-label learning from single positive labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 933–942 (2021)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018)
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702–703 (2020)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98–136 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Jiang, P.T., Yang, Y., Hou, Q., Wei, Y.: L2G: a simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16886–16896 (2022)
Kim, Y., Kim, J.M., Akata, Z., Lee, J.: Large loss matters in weakly supervised multi-label classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14156–14165 (2022)
Kim, Y., Kim, J.M., Jeong, J., Schmid, C., Akata, Z., Lee, J.: Bridging the gap between model explanations in partially annotated multi-label classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3408–3417 (2023)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lee, S., Lee, M., Lee, J., Shim, H.: Railroad is not a train: saliency as pseudo-pixel supervision for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021, pp. 5495–5505 (2021)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V 13. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, S., Zhang, L., Yang, X., Su, H., Zhu, J.: Query2Label: a simple transformer way to multi-label classification. arXiv preprint arXiv:2107.10834 (2021)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Lukasik, M., Bhojanapalli, S., Menon, A., Kumar, S.: Does label smoothing mitigate label noise? In: International Conference on Machine Learning, pp. 6448–6458. PMLR (2020)
Rajeswar, S., Rodriguez, P., Singhal, S., Vazquez, D., Courville, A.: Multi-label iterated learning for image classification with label ambiguity. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4783–4793 (2022)
Ridnik, T., et al.: Asymmetric loss for multi-label classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 82–91 (2021)
Ridnik, T., Sharir, G., Ben-Cohen, A., Ben-Baruch, E., Noy, A.: ML-Decoder: scalable and versatile classification head. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 32–41 (2023)
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: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, vol. 33, pp. 596–608 (2020)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Verelst, T., Rubenstein, P.K., Eichner, M., Tuytelaars, T., Berman, M.: Spatial consistency loss for training multi-label classifiers from single-label annotations. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3879–3889 (2023)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset (2011)
Wang, Y., Zhang, J., Kan, M., Shan, S., Chen, X.: Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Xie, M.K., Xiao, J., Huang, S.J.: Label-aware global consistency for multi-label learning with single positive labels. In: Advances in Neural Information Processing Systems, vol. 35, pp. 18430–18441 (2022)
Xie, Q., Dai, Z., Hovy, E., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6256–6268 (2020)
Yun, S., Oh, S.J., Heo, B., Han, D., Choe, J., Chun, S.: Re-labeling ImageNet: from single to multi-labels, from global to localized labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2340–2350 (2021)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Zhou, D., Chen, P., Wang, Q., Chen, G., Heng, P.A.: Acknowledging the unknown for multi-label learning with single positive labels. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13684, pp. 423–440. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20053-3_25
Zhou, T., Zhang, M., Zhao, F., Li, J.: Regional semantic contrast and aggregation for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4299–4309 (2022)
Acknowledgements
This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019-0-00421, AI Graduate School Support Program), the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (RS-2024-00352717), and institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. RS-2024-00437633, Development of Open-ended Alignment Fluxional AI for Ever-changing Environment and Value)
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
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Song, G., Kim, Nr., Lee, JS., Lee, JH. (2025). IGNORE: Information Gap-Based False Negative Loss Rejection for Single Positive Multi-Label Learning. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15092. Springer, Cham. https://doi.org/10.1007/978-3-031-72754-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-72754-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72753-5
Online ISBN: 978-3-031-72754-2
eBook Packages: Computer ScienceComputer Science (R0)