Self-Supervised Generative Intelligence for Automated
Keywords:
Capsule Networks, Medical Imaging, Self-Supervised Learning, Unsupervised Pretraining, Interpretable Deep Learning, Anomaly Detection, Generative Pretext Tasks, Latent Representation Learning, Multimodal Reconstruction, Domain-Agnostic Encoding, Perceptual Consistency, Explainable AI, Clinical Decision Support, Robust Feature Learning, Transfer Learning, Capsule Representation, Reconstruction-Based Learning, Healthcare AI Deployment, Model Interpretability, Clinical Imaging Analytics.Abstract
Capsule-based architectures have shown promise in medical imaging as compact, interpretable deep-learning models. Since annotation costs in this domain are often prohibitive, unsupervised pretraining offers an attractive alternative, and self-supervised learning in particular allows models to exploit unlabeled data while remaining perceptually aligned with the downstream task — improving both robustness and transferability. Building on this, we propose a self-supervised learning framework for capsule-based models, in which pretext tasks are designed to maximize the latent learning signal available in unlabeled data for both capsule representation and interpretation.
Capsule representation is central to this approach: by using capsule-based encodings for generative pretext tasks, the framework supports reconstruction of the input modality or any other modality within the dataset, yielding a domain-agnostic and perceptually consistent form of capsule encoding. This design is applied to two downstream objectives — anomaly detection and generating explanations for classification outcomes. We evaluate the full pipeline across multiple datasets, and the results demonstrate a clinically relevant improvement in performance, laying the groundwork for practical clinical deployment.
References
1. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. Proceedings of the 37th International Conference on Machine Learning, 119, 1597–1607.
2. He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9729–9738.
3. Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. Á., Guo, Z. D., Azar, M. G., Piot, B., Kavukcuoglu, K., Munos, R., & Valko, M. (2020). Bootstrap your own latent: A new approach to self-supervised learning. Advances in Neural Information Processing Systems, 33, 21271–21284.
4. Bhandari, P., Prithviraj, J., Saxena, R., Kumar, D., Mangala, N., & Chourasiya, P. (2026). Harris Hawks Optimization–Based Deep Learning for Resource-Aware Cloud–Fog Computing. In 2026 5th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0 (pp. 1–6). IEEE. 2026 5th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0. https://doi.org/10.1109/otcon69332.2026.11629982
5. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. Advances in Neural Information Processing Systems, 33, 9912–9924.
6. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
7. Chen, M., Radford, A., Child, R., Wu, J., Jun, H., Luan, D., & Sutskever, I. (2020). Generative pretraining from pixels. Proceedings of the 37th International Conference on Machine Learning, 119, 1691–1703.
8. A, R., Maheswari, N. U., Umamaheswari, P., Josephson, P. J., Mangalampalli, B. M., & Gudada, P. V. (2026). Tree-Structured Regularization Driven CNN Model for Liver Disease Diagnosis and Classification Using Ultrasound Imaging. In 2026 International Conference on Intelligent and Sustainable Electronics & Computing Technologies (INSECT) (pp. 1–6). IEEE. 2026 International Conference on Intelligent and Sustainable Electronics & Computing Technologies (INSECT). https://doi.org/10.1109/insect68872.2026.11663742
9. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
10. Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. Proceedings of the 38th International Conference on Machine Learning, 139, 8748–8763.
11. Caron, M., Touvron, H., Misra, I., Jégou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision, 9650–9660.
12. Jogi, N. L., Kumar, K. R., Mangala, N., M.Govindarajan, Gamini, P., & Bundhe, S. (2026). Machine Learning-Based Random Forest Model for Sustainable Supply Chain Sales Forecasting. In 2026 6th International Conference on Intelligent Technologies (CONIT) (pp. 1–6). IEEE. 2026 6th International Conference on Intelligent Technologies (CONIT). https://doi.org/10.1109/conit69683.2026.11620788
13. Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. Á., Guo, Z. D., Azar, M. G., Piot, B., Kavukcuoglu, K., Munos, R., & Valko, M. (2021). Bootstrap your own latent: A new approach to self-supervised learning. Advances in Neural Information Processing Systems, 34, 21271–21284.
14. He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16000–16009.
15. Bao, H., Dong, L., Piao, S., & Wei, F. (2022). BEiT: BERT pre-training of image transformers. International Conference on Learning Representations.
16. Baevski, A., Hsu, W.-N., Xu, Q., Babu, A., Gu, J., & Auli, M. (2022). Data2vec: A general framework for self-supervised learning in speech, vision and language. Proceedings of the 39th International Conference on Machine Learning, 162, 1298–1312.
17. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10684–10695.
18. Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, K., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., Salimans, T., Ho, J., Fleet, D. J., & Norouzi, M. (2022). Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35, 36479–36494.
19. Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., Ring, R., Rutherford, E., Cabi, S., Han, T., Gong, Z., Samangooei, S., Monteiro, M., Menick, J., Borgeaud, S., ... Simonyan, K. (2022). Flamingo: A visual language model for few-shot learning. Advances in Neural Information Processing Systems, 35, 23716–23736.
20. Li, J., Li, D., Xiong, C., & Hoi, S. (2022). BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. Proceedings of the 39th International Conference on Machine Learning, 162, 12888–12900.
21. Zhou, C., Li, Q., Li, C., Yu, J., Liu, Y., Wang, G., Zhang, K., Ji, C., Yan, Q., He, L., Peng, H., Li, J., Wu, J., Liu, Z., Xie, P., Xiong, C., Pei, J., Yu, P. S., & Sun, L. (2023). A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT. International Journal of Machine Learning and Cybernetics.
22. Wang, Y., Kordi, Y., Mishra, S., Liu, A., Smith, N. A., Khashabi, D., & Hajishirzi, H. (2023). Self-Instruct: Aligning language models with self-generated instructions. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 13484–13508.
23. Li, J., Li, D., Savarese, S., & Hoi, S. (2023). BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. Proceedings of the 40th International Conference on Machine Learning, 202, 19730–19742.
24. Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual instruction tuning. Advances in Neural Information Processing Systems, 36, 34892–34916.
25. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744.
26. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., Bikel, D., Blecher, L., Ferrer, C. C., Chen, M., Cucurull, G., Esiobu, M., Fernandes, J., Fu, J., Fu, W., ... Scialom, T. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
27. Malhotra, A., Niharika, D. S., Mangalampalli, B. M., Nema, S., Gupta, Z., & Kriplani, K. (2026, June). Distributed and Edge AI for Continuous and Context-Aware Healthcare Intelligence. In 2026 5th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0 (pp. 1-6). IEEE.
28. Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Yang, A., Fan, A., Goyal, A., Hartshorn, A., Yang, A., Mitra, A., Sravankumar, A., Korenev, A., Hinsvark, A., Rao, A., Zhang, A., ... Ganesh, A. (2024). The Llama 3 herd of models. arXiv preprint arXiv:2407.21783.
29. Gui, J., Chen, T., Zhang, J., Cao, Q., Sun, Z., Luo, H., & Tao, D. (2024). A survey on self-supervised learning: Algorithms, applications, and future trends. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9052–9071.
30. Liu, F., Zhang, T., Dai, W., Zhang, C., Cai, W., Zhou, X., & Chen, D. (2024). Few-shot adaptation of multi-modal foundation models: A survey. Artificial Intelligence Review, 57, 268.
31. Zhou, J., Chen, Y., Hong, Z., Chen, W., et al. (2024). Training and serving system of foundation models: A comprehensive survey. IEEE Open Journal of the Computer Society, 5, 107–119.
32. Girdhar, R., El-Nouby, A., Liu, Z., Singh, M., Alwala, K. V., Joulin, A., & Misra, I. (2023). ImageBind: One embedding space to bind them all. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 15180–15190.
33. Gui, J., Chen, T., Zhang, J., Cao, Q., Sun, Z., Luo, H., & Tao, D. (2025). A survey on self-supervised learning: Recent advances and open problems. Neurocomputing, 655, 131409.
34. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N., Chen, A., Creel, K., Davis, J. Q., Demszky, D., ... Liang, P. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258.
