Roberto Alcover-Couso
Roberto Alcover-Couso has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Juan Carlos SanMiguel
Universidad Autónoma de Madrid
6 shared publications - Marcos Escudero-Viñolo
Universidad Autónoma de Madrid
5 shared publications - Jose Maria Martinez
Universidad Autónoma de Madrid
2 shared publications Andrea Pilzer
NVIDIA AI Technology Center Italy
1 shared publicationAndrei Bursuc
Valeo.ai France
1 shared publicationAngela Yao
Aalto University Finland
1 shared publication
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 544-564
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
- 10 September 2026
- Published by Springer Nature
- p. 544-564
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
- 20 September 2025
- Published by Springer Nature
- p. 397-407
Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
- 20 September 2025
- Published by Springer Nature
- p. 397-407
Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
- Open Access
- 17 April 2025
- Published by Elsevier in Pattern Recognition
- Vol. 166
Gradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks
- 17 April 2025
- Published by Elsevier in Pattern Recognition
- Vol. 166
Open AccessGradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 19 (1)
Controlling semantics of diffusion‐augmented data for unsupervised domain adaptation
Unsupervised domain adaptation (UDA) offers a compelling solution to bridge the gap between labelled synthetic data and unlabelled real‐world data for training semantic segmentation models, given the high costs associated with manual annotation. However, the visual differences between the synthetic and real images pose significant challenges to their practical applications. This work addresses these challenges through synthetic‐to‐real style transfer leveraging diffusion models. The authors’ proposal incorporates semantic controllers to guide the diffusion process and low‐rank adaptations (LoRAs) to ensure that style‐transferred images align with real‐world aesthetics while preserving semantic layout. Moreover, the authors introduce quality metrics to rank the utility of generated images, enabling the selective use of high‐quality images for training. To further enhance reliability, the authors propose a novel loss function that mitigates artefacts from the style transfer process by incorporating only pixels aligned with the original semantic labels. Experimental results demonstrate that the authors’ proposal outperforms selected state‐of‐the‐art methods for image generation and UDA training, achieving optimal performance even with a smaller set of high‐quality generated images. The authors’ code and models are available at http://www‐vpu.eps.uam.es/ControllingSem4UDA/ .
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 19 (1)
Open AccessControlling semantics of diffusion‐augmented data for unsupervised domain adaptation
Unsupervised domain adaptation (UDA) offers a compelling solution to bridge the gap between labelled synthetic data and unlabelled real‐world data for training semantic segmentation models, given the high costs associated with manual annotation. However, the visual differences between the synthetic and real images pose significant challenges to their practical applications. This work addresses these challenges through synthetic‐to‐real style transfer leveraging diffusion models. The authors’ proposal incorporates semantic controllers to guide the diffusion process and low‐rank adaptations (LoRAs) to ensure that style‐transferred images align with real‐world aesthetics while preserving semantic layout. Moreover, the authors introduce quality metrics to rank the utility of generated images, enabling the selective use of high‐quality images for training. To further enhance reliability, the authors propose a novel loss function that mitigates artefacts from the style transfer process by incorporating only pixels aligned with the original semantic labels. Experimental results demonstrate that the authors’ proposal outperforms selected state‐of‐the‐art methods for image generation and UDA training, achieving optimal performance even with a smaller set of high‐quality generated images. The authors’ code and models are available at http://www‐vpu.eps.uam.es/ControllingSem4UDA/ .
- Open Access
Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the abundance of freely accessible trained models to introduce a cost-free approach to model merging. It focuses on a layer-wise integration of merged models, aiming to maintain the distinctiveness of the task-specific final layers while unifying the initial layers, which are primarily associated with feature extraction. This approach ensures parameter consistency across all layers, essential for boosting performance. Moreover, it facilitates seamless integration of knowledge, enabling effective merging of models from different datasets and tasks. Specifically, we investigate its applicability in Unsupervised Domain Adaptation (UDA), an unexplored area for model merging, for Semantic and Panoptic Segmentation. Experimental results demonstrate substantial UDA improvements without additional costs for merging same-architecture models from distinct datasets ($\uparrow 2.6\%$ mIoU) and different-architecture models with a shared backbone ($\uparrow 6.8\%$ mIoU). Furthermore, merging Semantic and Panoptic Segmentation models increases mPQ by $\uparrow 7\%$. These findings are validated across a wide variety of UDA strategies, architectures, and datasets.Open AccessLayer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the abundance of freely accessible trained models to introduce a cost-free approach to model merging. It focuses on a layer-wise integration of merged models, aiming to maintain the distinctiveness of the task-specific final layers while unifying the initial layers, which are primarily associated with feature extraction. This approach ensures parameter consistency across all layers, essential for boosting performance. Moreover, it facilitates seamless integration of knowledge, enabling effective merging of models from different datasets and tasks. Specifically, we investigate its applicability in Unsupervised Domain Adaptation (UDA), an unexplored area for model merging, for Semantic and Panoptic Segmentation. Experimental results demonstrate substantial UDA improvements without additional costs for merging same-architecture models from distinct datasets ($\uparrow 2.6\%$ mIoU) and different-architecture models with a shared backbone ($\uparrow 6.8\%$ mIoU). Furthermore, merging Semantic and Panoptic Segmentation models increases mPQ by $\uparrow 7\%$. These findings are validated across a wide variety of UDA strategies, architectures, and datasets. - Open Access
- 15 April 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (2) , 901-919
Per-class curriculum for Unsupervised Domain Adaptation in semantic segmentation
Accurate training of deep neural networks for semantic segmentation requires a large number of pixel-level annotations of real images, which are expensive to generate or not even available. In this context, Unsupervised Domain Adaptation (UDA) can transfer knowledge from unlimited synthetic annotations to unlabeled real images of a given domain. UDA methods are composed of an initial training stage with labeled synthetic data followed by a second stage for feature alignment between labeled synthetic and unlabeled real data. In this paper, we propose a novel approach for UDA focusing the initial training stage, which leads to increased performance after adaptation. We introduce a curriculum strategy where each semantic class is learned progressively. Thereby, better features are obtained for the second stage. This curriculum is based on: (1) a class-scoring function to determine the difficulty of each semantic class, (2) a strategy for incremental learning based on scoring and pacing functions that limits the required training time unlike standard curriculum-based training and (3) a training loss to operate at class level. We extensively evaluate our approach as the first stage of several state-of-the-art UDA methods for semantic segmentation. Our results demonstrate significant performance enhancements across all methods: improvements of up to 10% for entropy-based techniques and 8% for adversarial methods. These findings underscore the dependency of UDA on the accuracy of the initial training. The implementation is available at https://github.com/vpulab/PCCL.
- 15 April 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (2) , 901-919
Open AccessPer-class curriculum for Unsupervised Domain Adaptation in semantic segmentation
Accurate training of deep neural networks for semantic segmentation requires a large number of pixel-level annotations of real images, which are expensive to generate or not even available. In this context, Unsupervised Domain Adaptation (UDA) can transfer knowledge from unlimited synthetic annotations to unlabeled real images of a given domain. UDA methods are composed of an initial training stage with labeled synthetic data followed by a second stage for feature alignment between labeled synthetic and unlabeled real data. In this paper, we propose a novel approach for UDA focusing the initial training stage, which leads to increased performance after adaptation. We introduce a curriculum strategy where each semantic class is learned progressively. Thereby, better features are obtained for the second stage. This curriculum is based on: (1) a class-scoring function to determine the difficulty of each semantic class, (2) a strategy for incremental learning based on scoring and pacing functions that limits the required training time unlike standard curriculum-based training and (3) a training loss to operate at class level. We extensively evaluate our approach as the first stage of several state-of-the-art UDA methods for semantic segmentation. Our results demonstrate significant performance enhancements across all methods: improvements of up to 10% for entropy-based techniques and 8% for adversarial methods. These findings underscore the dependency of UDA on the accuracy of the initial training. The implementation is available at https://github.com/vpulab/PCCL.
- Open Access
Soft labelling for semantic segmentation: Bringing coherence to label down-sampling
In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies for the image data and the annotated labels. Such discrepancy leads to mismatches between the down-sampled color and label images. Hence, the training performance significantly decreases as the down-sampling factor increases. In this paper, we bring together the down-sampling strategies for the image data and the training labels. To that aim, we propose a novel framework for label down-sampling via soft-labeling that better conserves label information after down-sampling. Therefore, fully aligning soft-labels with image data to keep the distribution of the sampled pixels. This proposal also produces reliable annotations for under-represented semantic classes. Altogether, it allows training competitive models at lower resolutions. Experiments show that the proposal outperforms other down-sampling strategies. Moreover, state-of-the-art performance is achieved for reference benchmarks, but employing significantly less computational resources than foremost approaches. This proposal enables competitive research for semantic segmentation under resource constraints.
Open AccessSoft labelling for semantic segmentation: Bringing coherence to label down-sampling
In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies for the image data and the annotated labels. Such discrepancy leads to mismatches between the down-sampled color and label images. Hence, the training performance significantly decreases as the down-sampling factor increases. In this paper, we bring together the down-sampling strategies for the image data and the training labels. To that aim, we propose a novel framework for label down-sampling via soft-labeling that better conserves label information after down-sampling. Therefore, fully aligning soft-labels with image data to keep the distribution of the sampled pixels. This proposal also produces reliable annotations for under-represented semantic classes. Altogether, it allows training competitive models at lower resolutions. Experiments show that the proposal outperforms other down-sampling strategies. Moreover, state-of-the-art performance is achieved for reference benchmarks, but employing significantly less computational resources than foremost approaches. This proposal enables competitive research for semantic segmentation under resource constraints.
- Open Access
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.
Open AccessThe Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.
- Open Access
- 11 March 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (23) , 35879-35911
On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
Pixel-wise image segmentation is key for many Computer Vision applications. The training of deep neural networks for this task has expensive pixel-level annotation requirements, thus, motivating a growing interest on synthetic data to provide unlimited data and its annotations. In this paper, we focus on the generation and application of synthetic data as representative training corpuses for semantic segmentation of urban scenes. First, we propose a synthetic data generation protocol, which identifies key features affecting performance and provides datasets with variable complexity. Second, we adapt two popular weakly supervised domain adaptation approaches (combined training, fine-tuning) to employ synthetic and real data. Moreover, we analyze several backbone models, real/synthetic datasets and their proportions when combined. Third, we propose a new curriculum learning strategy to employ several synthetic and real datasets. Our major findings suggest the high performance impact of pace and order of synthetic and real data presentation, achieving state of the art results for well-known models. The results by training with the proposed dataset outperform popular alternatives, thus demonstrating the effectiveness of the proposed protocol. Our code and dataset are available at http://www-vpu.eps.uam.es/publications/WSDA_semantic/
- 11 March 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (23) , 35879-35911
Open AccessOn exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
Pixel-wise image segmentation is key for many Computer Vision applications. The training of deep neural networks for this task has expensive pixel-level annotation requirements, thus, motivating a growing interest on synthetic data to provide unlimited data and its annotations. In this paper, we focus on the generation and application of synthetic data as representative training corpuses for semantic segmentation of urban scenes. First, we propose a synthetic data generation protocol, which identifies key features affecting performance and provides datasets with variable complexity. Second, we adapt two popular weakly supervised domain adaptation approaches (combined training, fine-tuning) to employ synthetic and real data. Moreover, we analyze several backbone models, real/synthetic datasets and their proportions when combined. Third, we propose a new curriculum learning strategy to employ several synthetic and real datasets. Our major findings suggest the high performance impact of pace and order of synthetic and real data presentation, achieving state of the art results for well-known models. The results by training with the proposed dataset outperform popular alternatives, thus demonstrating the effectiveness of the proposed protocol. Our code and dataset are available at http://www-vpu.eps.uam.es/publications/WSDA_semantic/