Abstract
This article proposes a Neuro-Symbolic (NeSy) machine learning approach to Object Re-identification. NeSy is an emerging branch of artificial intelligence which combines symbolic reasoning and logic-based knowledge representation with the learning capabilities of neural networks. Since object re-identification involves assigning the identity of the same object across different images and different conditions, such a task could benefit greatly from leveraging the logic capabilities of a NeSy framework to inject prior knowledge about invariant properties of the objects. To test this assertion, we combined the Logic Tensor Networks (LTNs) NeSy framework with a state-of-the-art Transformer-based Re-Identification and Damage Detection Network (TransRe3ID). The LTN incorporates prior knowledge about the properties that two instances of the same object have in common. Experimental results on the Bent&Broken Bicycle re-identification dataset demonstrate the potential of LTNs to improve re-identification systems and provide novel opportunities to identify pitfalls during training.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Badreddine, S., Garcez, A.D., Serafini, L., Spranger, M.: Logic tensor networks. Artif. Intell. 303, 103649 (2022)
Badreddine, S., Spranger, M.: Injecting prior knowledge for transfer learning into reinforcement learning algorithms using logic tensor networks. arXiv preprint arXiv:1906.06576 (2019)
Chen, B., Marussy, K., Pilarski, S., Semeráth, O., Varro, D.: Consistent scene graph generation by constraint optimization. In: Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, pp. 1–13 (2022)
Donadello, I., Serafini, L.: Compensating supervision incompleteness with prior knowledge in semantic image interpretation. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2019)
Dutta, S., Basu, S., Chakraborty, M.K.: Many-valued logics, fuzzy logics and graded consequence: a comparative appraisal. In: Lodaya, K. (ed.) ICLA 2013. LNCS, vol. 7750, pp. 197–209. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-36039-8_18
Garcez, A.d., Gori, M., Lamb, L.C., Serafini, L., Spranger, M., Tran, S.N.: Neural-symbolic computing: an effective methodology for principled integration of machine learning and reasoning. arXiv preprint arXiv:1905.06088 (2019)
Garcez, A.D., Lamb, L.C.: Neurosymbolic AI: the 3rd wave. In: Artificial Intelligence Review, pp. 1–20 (2023)
Gibaut, W., et al.: Neurosymbolic AI and its taxonomy: a survey. arXiv e-prints pp. arXiv-2305 (2023)
He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: TransReID: transformer-based object re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15013–15022 (2021)
Hitzler, P.: Neuro-symbolic artificial intelligence: the state of the art (2022)
Huang, H., Zhang, B., Jing, L., Fu, X., Chen, X., Shi, J.: Logic tensor network with massive learned knowledge for aspect-based sentiment analysis. Knowl.-Based Syst. 257, 109943 (2022)
Khan, M.J., Breslin, J.G., Curry, E.: Expressive scene graph generation using commonsense knowledge infusion for visual understanding and reasoning. In: Groth, P., et al. (eds.) ESWC 2022. Lecture Notes in Computer Science, vol. 13261, pp. 93–112. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06981-9_6
van Krieken, E., Acar, E., van Harmelen, F.: Analyzing differentiable fuzzy logic operators. Artif. Intell. 302, 103602 (2022)
Lian, J., Wang, D., Zhu, S., Wu, Y., Li, C.: Transformer-based attention network for vehicle re-identification. Electronics 11(7), 1016 (2022)
Lu, Z., Lin, R., Hu, H.: MART: mask-aware reasoning transformer for vehicle re-identification. IEEE Trans. Intell. Transp. Syst. 24, 1994–2009 (2022)
Ma, H., Li, X., Yuan, X., Zhao, C.: Denseformer: a dense transformer framework for person re-identification. IET Comput. Vision 17, 527–536 (2022)
Manigrasso, F., Miro, F.D., Morra, L., Lamberti, F.: Faster-LTN: a neuro-symbolic, end-to-end object detection architecture. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12892, pp. 40–52. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86340-1_4
Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B., Wu, J.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. In: International Conference on Learning Representations. International Conference on Learning Representations, ICLR (2019)
Martone, S., Manigrasso, F., Lamberti, F., Morra, L.: Prototypical logic tensor networks (proto-LTN) for zero shot learning. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 4427–4433. IEEE (2022)
Park, J., Bu, S.J., Cho, S.B.: A neuro-symbolic AI system for visual question answering in pedestrian video sequences. In: Bringas, P.G., et al. (eds.) HAIS 2022. LNCS, vol. 13469, pp. 443–454. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-15471-3_38
Piano, L., Pratticò, F.G., Russo, A.S., Lanari, L., Morra, L., Lamberti, F.: Bent & broken bicycles: leveraging synthetic data for damaged object re-identification. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 4881–4891 (2023)
Serafini, L., Donadello, I., Garcez, A.D.: Learning and reasoning in logic tensor networks: theory and application to semantic image interpretation. In: Proceedings of the Symposium on Applied Computing, pp. 125–130 (2017)
Silver, T., Athalye, A., Tenenbaum, J.B., Lozano-Pérez, T., Kaelbling, L.P.: Learning neuro-symbolic skills for bilevel planning. In: Conference on Robot Learning, pp. 701–714. PMLR (2023)
Wang, H., Shen, J., Liu, Y., Gao, Y., Gavves, E.: NFormer: robust person re-identification with neighbor transformer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7297–7307 (2022)
Wu, T., et al.: ZeroC: a neuro-symbolic model for zero-shot concept recognition and acquisition at inference time. In: Advances in Neural Information Processing Systems, vol. 35, pp. 9828–9840 (2022)
Yu, Z., Pei, J., Zhu, M., Zhang, J., Li, J.: Multi-attribute adaptive aggregation transformer for vehicle re-identification. Inf. Process. Manage. 59(2), 102868 (2022)
Zhu, K., et al.: Aaformer: auto-aligned transformer for person re-identification. IEEE Trans. Neural Netw. Learn. Syst. (2023)
Acknowledgements
This study was carried out within the FAIR - Future Artificial Intelligence Research and received funding from the European Union Next-GenerationEU (PIANO NAZIONALE DI RIPRESA E RESILIENZA (PNRR) - MISSIONE 4 COMPONENTE 2, INVESTIMENTO 1.3 - D.D. 1555 11/10/2022, PE00000013). This manuscript reflects only the authors’ views and opinions, neither the European Union nor the European Commission can be considered responsible for them.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Alessandro, R., Francesco, M., Fabrizio, L., Lia, M. (2023). L-TReiD: Logic Tensor Transformer for Re-identification. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2023. Lecture Notes in Computer Science, vol 14362. Springer, Cham. https://doi.org/10.1007/978-3-031-47966-3_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-47966-3_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47965-6
Online ISBN: 978-3-031-47966-3
eBook Packages: Computer ScienceComputer Science (R0)