Abstract
Multi-label recognition with limited annotations has been gaining attention recently due to the costs of thorough dataset annotation. Despite significant progress, current methods for simulating partial labels utilize a strategy that uniformly omits labels, which inadequately prepares models for real-world inconsistencies and undermines their generalization performance. In this paper, we consider a more realistic partial label setting that correlates label absence with an instance’s ambiguity, and propose the novel Ambiguity-Aware Instance Weighting (AAIW) to specifically address the performance decline caused by such ambiguous instances. This strategy dynamically modulates instance weights to prioritize learning from less ambiguous instances initially, then gradually increasing the weight of complex examples without the need for predetermined sequencing of data. This adaptive weighting not only facilitates a more natural learning progression but also enhances the model’s ability to generalize from increasingly complex patterns. Experiments on standard multi-label recognition benchmarks demonstrate the advantages of our approach over state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmad, M., Lee, S.W.: Human action recognition using multi-view image sequences. In: ICAFGR, pp. 523 – 528 (2006)
Baruch, E.B., et al.: Asymmetric loss for multi-label classification. In: ICCV, pp. 82–91 (2020)
Ben-Baruch, E., et al.: Multi-label classification with partial annotations using class-aware selective loss. In: CVPR, pp. 4754–4762 (2021)
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML, pp. 41–48 (2009)
Chen, M., Zheng, A.X., Weinberger, K.Q.: Fast image tagging. In: ICML (2013)
Chen, T., Pu, T., Wu, H., Xie, Y., Lin, L.: Structured semantic transfer for multi-label recognition with partial labels. In: AAAI, pp. 339–346 (2022)
Chen, T., Xu, M., Hui, X., Wu, H., Lin, L.: Learning semantic-specific graph representation for multi-label image recognition. In: ICCV, pp. 522–531 (2019)
Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: CVPR (2019)
Cole, E., Mac Aodha, O., Lorieul, T., Perona, P., Morris, D., Jojic, N.: Multi-label learning from single positive labels. In: CVPR (2021)
Ding, Z., et al.: Exploring structured semantic prior for multi label recognition with incomplete labels. In: CVPR, pp. 3398–3407 (2023)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)
He, S., Guo, T., Dai, T., Qiao, R., Shu, X., Ren, B., Xia, S.T.: Open-vocabulary multi-label classification via multi-modal knowledge transfer. In: AAAI (2023)
Huynh, D., Elhamifar, E.: Interactive multi-label CNN learning with partial labels. In: CVPR (2020)
Kapoor, A., Jain, P., Viswanathan, R.: Multilabel classification using bayesian compressed sensing. In: NeurIPS, pp. 2645–2653 (2012)
Kim, Y., Kim, J., Akata, Z., Lee, J.: Large loss matters in weakly supervised multi-label classification. In: CVPR, pp. 14136–14145 (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: CVPR, pp. 3408–3417 (2023)
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32–73 (2017)
Lee, M.S., Yang, Y.M., Lee, S.W.: Automatic video parsing using shot boundary detection and camera operation analysis. Pattern Recogn. 34, 711–719 (2001)
Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV, pp. 740–755 (2014)
Litrico, M., Del Bue, A., Morerio, P.: Guiding pseudo-labels with uncertainty estimation for source-free unsupervised domain adaptation. In: CVPR (2023)
Liu, F., Xiang, T., Hospedales, T.M., Yang, W., Sun, C.: Semantic regularisation for recurrent image annotation. In: CVPR, pp. 4160–4168 (2016)
Liu, W., Wang, H., Shen, X., Tsang, I.W.H.: The emerging trends of multi-label learning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7955–7974 (2020)
Mitchell, H.B., Schaefer, P.A.: A “soft” k-nearest neighbor voting scheme. Int. J. Intell. Syst. 16(4), 459–468 (2001)
Nam, W.J., Gur, S., Choi, J., Wolf, L., Lee, S.W.: Relative attributing propagation: interpreting the comparative contributions of individual units in deep neural networks. In: AAAI, pp. 2501–2508 (2020)
Park, L.A.F., Simoff, S.: Using entropy as a measure of acceptance for multi-label classification. In: Advances in Intelligent Data Analysis XIV, pp. 217–228 (2015)
Pu, T., Chen, T., Wu, H., Lin, L.: Semantic-aware representation blending for multi-label image recognition with partial labels. In: AAAI, pp. 2091–2098 (2022)
Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)
Rajeswar, S., López, P.R., Singhal, S., Vázquez, D., Courville, A.C.: Multi-label iterated learning for image classification with label ambiguity. In: CVPR, pp. 4773–4783 (2021)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Sun, X., Hu, P., Saenko, K.: Dualcoop: fast adaptation to multi-label recognition with limited annotations. In: NeurIPS (2022)
Vasisht, D., Damianou, A., Varma, M., Kapoor, A.: Active learning for sparse bayesian multilabel classification. In: SIGKDD, pp. 472–481 (2014)
Wang, Y., et al.: Multi-label classification with label graph superimposing. In: AAAI, vol. 34, pp. 12265–12272 (2020)
Wu, B., Liu, Z., Wang, S., Hu, B.G., Ji, Q.: Multi-label learning with missing labels. In: ICPR, pp. 1964–1968 (2014)
Zhang, B., et al.: Flexmatch: boosting semi-supervised learning with curriculum pseudo labeling. In: NeurIPS, vol. 34, pp. 18408–18419 (2021)
Zhang, X., Song, Y., Zuo, F., Wang, X.: Towards imbalanced large scale multi-label classification with partially annotated labels. In: SERA, pp. 195–200 (2023)
Zhang, Y., et al.: Simple and robust loss design for multi-label learning with missing labels. arXiv abs/2112.07368 (2021)
Zhou, D., Chen, P., Wang, Q., Chen, G., Heng, P.A.: Acknowledging the unknown for multi-label learning with single positive labels. arXiv abs/2203.16219 (2022)
Acknowledgement
This research was supported by the Challengeable Future Defense Technology Research and Development Program through the Agency For Defense Development (ADD) funded by the Defense Acquisition Program Administration (DAPA) in 2024 (No.912911601) and was partly supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant, funded by the Korea government (MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program (Korea University)) and NCSOFT corporation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shrewsbury, D., Kim, S., Kim, YE., Kong, H., Lee, SW. (2024). Instance-Ambiguity Weighting for Multi-label Recognition with Limited Annotations. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14645. Springer, Singapore. https://doi.org/10.1007/978-981-97-2242-6_13
Download citation
DOI: https://doi.org/10.1007/978-981-97-2242-6_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2241-9
Online ISBN: 978-981-97-2242-6
eBook Packages: Computer ScienceComputer Science (R0)