Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Nouboukpo, A.; Allili, M. S.
Semi-supervised flow-augmented Gaussian mixture VAEs with weighted contrastive learning for out-of-distribution detection Journal Article
In: Knowledge-Based Systems, vol. 347, 2026, ISSN: 09507051 (ISSN).
Abstract | Links | BibTeX | Tags: Auto encoders, Benchmarking, Classification (of information), Clusterings, Contrastive Learning, Flow based, Flow-based GMM clustering, Gaussian distribution, Gaussian-mixtures, Learning algorithms, Learning systems, Out-of-distribution detection, Semantics, Semi-supervised, Semi-supervised learning, uncertainty, Variational autoencoder, Variational autoencoders (VAEs)
@article{nouboukpoSemisupervisedFlowaugmentedGaussian2026,
title = {Semi-supervised flow-augmented Gaussian mixture VAEs with weighted contrastive learning for out-of-distribution detection},
author = {A. Nouboukpo and M. S. Allili},
url = {https://www.scopus.com/pages/publications/105040505017?origin=resultslist},
doi = {10.1016/j.knosys.2026.116312},
issn = {09507051 (ISSN)},
year = {2026},
date = {2026-01-01},
journal = {Knowledge-Based Systems},
volume = {347},
publisher = {Elsevier B.V.},
abstract = {Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning systems, particularly in high-stakes domains where identifying inputs that deviate from the in-distribution (ID) is critical. However, in real-world scenarios, true OOD data are typically unavailable at training time, and only auxiliary datasets acting as imperfect proxies can be used. This makes fully supervised approaches impractical and potentially biased toward specific anomaly types. To address this limitation, we propose FLoW-ssGMVAE, a semi-supervised generative–discriminative framework that leverages limited proxy anomaly supervision together with abundant unlabeled data for robust OOD detection. Our model integrates a flow-augmented Gaussian Mixture VAE, enabling flexible latent modeling that captures nonlinear and multimodal intra-class distributions. Unlike standard VAEs with unimodal Gaussian priors, it uses class-conditional normalizing flows to better represent complex ID and OOD variability. To further refine the latent space and strengthen ID/OOD separation, our model integrates a weighted contrastive learning objective guided by sample-wise attention scores derived from likelihood uncertainty. This mechanism emphasizes ambiguous or hard-to-classify instances, reinforcing semantic boundaries and reducing false detections. By combining expressive generative modeling with uncertainty-aware discriminative training, our method constructs a structured and interpretable latent space that reliably identifies OOD samples under limited supervision. Experiments on standard benchmarks validate the effectiveness and scalability of our approach, demonstrating state-of-the-art performance with reasonable computational cost. Our implementation will be available at: FLoW-ssGMVAE. © 2026},
keywords = {Auto encoders, Benchmarking, Classification (of information), Clusterings, Contrastive Learning, Flow based, Flow-based GMM clustering, Gaussian distribution, Gaussian-mixtures, Learning algorithms, Learning systems, Out-of-distribution detection, Semantics, Semi-supervised, Semi-supervised learning, uncertainty, Variational autoencoder, Variational autoencoders (VAEs)},
pubstate = {published},
tppubtype = {article}
}
Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning systems, particularly in high-stakes domains where identifying inputs that deviate from the in-distribution (ID) is critical. However, in real-world scenarios, true OOD data are typically unavailable at training time, and only auxiliary datasets acting as imperfect proxies can be used. This makes fully supervised approaches impractical and potentially biased toward specific anomaly types. To address this limitation, we propose FLoW-ssGMVAE, a semi-supervised generative–discriminative framework that leverages limited proxy anomaly supervision together with abundant unlabeled data for robust OOD detection. Our model integrates a flow-augmented Gaussian Mixture VAE, enabling flexible latent modeling that captures nonlinear and multimodal intra-class distributions. Unlike standard VAEs with unimodal Gaussian priors, it uses class-conditional normalizing flows to better represent complex ID and OOD variability. To further refine the latent space and strengthen ID/OOD separation, our model integrates a weighted contrastive learning objective guided by sample-wise attention scores derived from likelihood uncertainty. This mechanism emphasizes ambiguous or hard-to-classify instances, reinforcing semantic boundaries and reducing false detections. By combining expressive generative modeling with uncertainty-aware discriminative training, our method constructs a structured and interpretable latent space that reliably identifies OOD samples under limited supervision. Experiments on standard benchmarks validate the effectiveness and scalability of our approach, demonstrating state-of-the-art performance with reasonable computational cost. Our implementation will be available at: FLoW-ssGMVAE. © 2026
2.
Nouboukpo, A.; Allaoui, M. L.; Allili, M. S.
Multi-scale spatial consistency for deep semi-supervised skin lesion segmentation Journal Article
In: Engineering Applications of Artificial Intelligence, vol. 135, 2024, ISSN: 09521976 (ISSN), (Publisher: Elsevier Ltd).
Abstract | Links | BibTeX | Tags: Deep learning, Dermatology, Image segmentation, Lesion segmentations, Medical imaging, Multi-scales, Semi-supervised, Semi-supervised learning, Skin lesion, Skin lesion segmentation, Spatial consistency, Spatially constrained mixture model, Spatially-constrained mixture models, Supervised learning, UNets, Unlabeled data
@article{nouboukpo_multi-scale_2024,
title = {Multi-scale spatial consistency for deep semi-supervised skin lesion segmentation},
author = {A. Nouboukpo and M. L. Allaoui and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195700182&doi=10.1016%2fj.engappai.2024.108681&partnerID=40&md5=e1cc2b6a1bb0aed530e8c04583c76167},
doi = {10.1016/j.engappai.2024.108681},
issn = {09521976 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Engineering Applications of Artificial Intelligence},
volume = {135},
publisher = {Elsevier Ltd},
abstract = {This paper introduces a novel semi-supervised framework, the Multiscale Spatial Consistency Network (MSCNet), for robust semi-supervised skin lesion segmentation. MSCNet uses local and global spatial consistency to leverage a minimal set of labeled data, supplemented by a large number of unlabeled data, to improve segmentation. The model is is based on a single Encoder–Decoder (ED) network, augmented with a Spatially-Constrained Mixture Model (SCMM) to enforce spatial coherence in predictions. To encode the local spatial consistency, a hierarchical superpixel structure is used capture local region context (LRC), bolstering the model capacity to discern fine-grained lesion details. Global consistency is enforced through the SCMM module, which uses a larger context for lesion/background discrimination. In addition, it enables efficient leveraging of the unlabeled data through pseudo-label generation. Experiments demonstrate that the MSCNet outperforms existing state-of-the-art methods in segmenting complex lesions. The MSCNet has an excellent generalization capability, offering a promising direction for semi-supervised medical image segmentation, particularly in scenarios with limited annotated data. The code is available at https://github.com/AdamaTG/MSCNet. © 2024 Elsevier Ltd},
note = {Publisher: Elsevier Ltd},
keywords = {Deep learning, Dermatology, Image segmentation, Lesion segmentations, Medical imaging, Multi-scales, Semi-supervised, Semi-supervised learning, Skin lesion, Skin lesion segmentation, Spatial consistency, Spatially constrained mixture model, Spatially-constrained mixture models, Supervised learning, UNets, Unlabeled data},
pubstate = {published},
tppubtype = {article}
}
This paper introduces a novel semi-supervised framework, the Multiscale Spatial Consistency Network (MSCNet), for robust semi-supervised skin lesion segmentation. MSCNet uses local and global spatial consistency to leverage a minimal set of labeled data, supplemented by a large number of unlabeled data, to improve segmentation. The model is is based on a single Encoder–Decoder (ED) network, augmented with a Spatially-Constrained Mixture Model (SCMM) to enforce spatial coherence in predictions. To encode the local spatial consistency, a hierarchical superpixel structure is used capture local region context (LRC), bolstering the model capacity to discern fine-grained lesion details. Global consistency is enforced through the SCMM module, which uses a larger context for lesion/background discrimination. In addition, it enables efficient leveraging of the unlabeled data through pseudo-label generation. Experiments demonstrate that the MSCNet outperforms existing state-of-the-art methods in segmenting complex lesions. The MSCNet has an excellent generalization capability, offering a promising direction for semi-supervised medical image segmentation, particularly in scenarios with limited annotated data. The code is available at https://github.com/AdamaTG/MSCNet. © 2024 Elsevier Ltd
3.
Nouboukpo, A.; Allaoui, M. L.; Allili, M. S.
Multi-scale spatial consistency for deep semi-supervised skin lesion segmentation Journal Article
In: Engineering Applications of Artificial Intelligence, vol. 135, 2024, ISSN: 09521976 (ISSN).
Abstract | Links | BibTeX | Tags: Deep learning, Dermatology, Image segmentation, Lesion segmentations, Medical imaging, Multi-scales, Semi-supervised, Semi-supervised learning, Skin lesion, Skin lesion segmentation, Spatial consistency, Spatially constrained mixture model, Spatially-constrained mixture models, Supervised learning, UNets, Unlabeled data
@article{nouboukpoMultiscaleSpatialConsistency2024,
title = {Multi-scale spatial consistency for deep semi-supervised skin lesion segmentation},
author = {A. Nouboukpo and M. L. Allaoui and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195700182&doi=10.1016%2fj.engappai.2024.108681&partnerID=40&md5=e1cc2b6a1bb0aed530e8c04583c76167},
doi = {10.1016/j.engappai.2024.108681},
issn = {09521976 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Engineering Applications of Artificial Intelligence},
volume = {135},
publisher = {Elsevier Ltd},
abstract = {This paper introduces a novel semi-supervised framework, the Multiscale Spatial Consistency Network (MSCNet), for robust semi-supervised skin lesion segmentation. MSCNet uses local and global spatial consistency to leverage a minimal set of labeled data, supplemented by a large number of unlabeled data, to improve segmentation. The model is is based on a single Encoder–Decoder (ED) network, augmented with a Spatially-Constrained Mixture Model (SCMM) to enforce spatial coherence in predictions. To encode the local spatial consistency, a hierarchical superpixel structure is used capture local region context (LRC), bolstering the model capacity to discern fine-grained lesion details. Global consistency is enforced through the SCMM module, which uses a larger context for lesion/background discrimination. In addition, it enables efficient leveraging of the unlabeled data through pseudo-label generation. Experiments demonstrate that the MSCNet outperforms existing state-of-the-art methods in segmenting complex lesions. The MSCNet has an excellent generalization capability, offering a promising direction for semi-supervised medical image segmentation, particularly in scenarios with limited annotated data. The code is available at https://github.com/AdamaTG/MSCNet. © 2024 Elsevier Ltd},
keywords = {Deep learning, Dermatology, Image segmentation, Lesion segmentations, Medical imaging, Multi-scales, Semi-supervised, Semi-supervised learning, Skin lesion, Skin lesion segmentation, Spatial consistency, Spatially constrained mixture model, Spatially-constrained mixture models, Supervised learning, UNets, Unlabeled data},
pubstate = {published},
tppubtype = {article}
}
This paper introduces a novel semi-supervised framework, the Multiscale Spatial Consistency Network (MSCNet), for robust semi-supervised skin lesion segmentation. MSCNet uses local and global spatial consistency to leverage a minimal set of labeled data, supplemented by a large number of unlabeled data, to improve segmentation. The model is is based on a single Encoder–Decoder (ED) network, augmented with a Spatially-Constrained Mixture Model (SCMM) to enforce spatial coherence in predictions. To encode the local spatial consistency, a hierarchical superpixel structure is used capture local region context (LRC), bolstering the model capacity to discern fine-grained lesion details. Global consistency is enforced through the SCMM module, which uses a larger context for lesion/background discrimination. In addition, it enables efficient leveraging of the unlabeled data through pseudo-label generation. Experiments demonstrate that the MSCNet outperforms existing state-of-the-art methods in segmenting complex lesions. The MSCNet has an excellent generalization capability, offering a promising direction for semi-supervised medical image segmentation, particularly in scenarios with limited annotated data. The code is available at https://github.com/AdamaTG/MSCNet. © 2024 Elsevier Ltd
4.
Nouboukpo, A.; Allili, M. S.
Weakly Semi Supervised learning based Mixture Model With Two-Level Constraints Proceedings Article
In: A., Premaratne K. Benferhot S. Antonucci (Ed.): Proceedings of the International Florida Artificial Intelligence Research Society Conference, FLAIRS, Florida Online Journals, University of Florida, 2021, ISSN: 23340754, (ISSN: 23340754).
Abstract | Links | BibTeX | Tags: Classification and clustering, Group structure, Learn+, Mixture components, Mixture modeling, Mixtures, Multilevels, Number of class, Prior-knowledge, Semi-supervised learning, Supervised learning, Unlabeled data
@inproceedings{nouboukpo_weakly_2021,
title = {Weakly Semi Supervised learning based Mixture Model With Two-Level Constraints},
author = {A. Nouboukpo and M. S. Allili},
editor = {Premaratne K. Benferhot S. Antonucci A.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131143535&doi=10.32473%2fflairs.v34i1.128490&partnerID=40&md5=21cda84d36649f4835be079ea2566717},
doi = {10.32473/flairs.v34i1.128490},
issn = {23340754},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the International Florida Artificial Intelligence Research Society Conference, FLAIRS},
volume = {34},
publisher = {Florida Online Journals, University of Florida},
abstract = {We propose a new weakly supervised approach for classification and clustering based on mixture models. Our approach integrates multi-level pairwise group and class constraints between samples to learn the underlying group structure of the data and propagate (scarce) initial labels to unlabelled data. Our algorithm assumes the number of classes is known but does not assume any prior knowledge about the number of mixture components in each class. Therefore, our model: (1) allocates multiple mixture components to individual classes, (2) estimates automatically the number of components of each class, 3) propagates class labels to unlabelled data in a consistent way to predefined constraints. Experiments on several real-world and synthetic data datasets show the robustness and performance of our model over state-of-the-art methods. © 2021 by the authors. All rights reserved.},
note = {ISSN: 23340754},
keywords = {Classification and clustering, Group structure, Learn+, Mixture components, Mixture modeling, Mixtures, Multilevels, Number of class, Prior-knowledge, Semi-supervised learning, Supervised learning, Unlabeled data},
pubstate = {published},
tppubtype = {inproceedings}
}
We propose a new weakly supervised approach for classification and clustering based on mixture models. Our approach integrates multi-level pairwise group and class constraints between samples to learn the underlying group structure of the data and propagate (scarce) initial labels to unlabelled data. Our algorithm assumes the number of classes is known but does not assume any prior knowledge about the number of mixture components in each class. Therefore, our model: (1) allocates multiple mixture components to individual classes, (2) estimates automatically the number of components of each class, 3) propagates class labels to unlabelled data in a consistent way to predefined constraints. Experiments on several real-world and synthetic data datasets show the robustness and performance of our model over state-of-the-art methods. © 2021 by the authors. All rights reserved.