Alban Marie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Alban Marie has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Alexandre Mercat
Ultra Video Group, Tampere University, Tampere, Finland
1 shared publication- Aline Roumy
Inria Rennes France
1 shared publication Jarno Vanne
Ultra Video Group, Tampere University, Tampere, Finland
1 shared publicationKarol Desnos
Univ Rennes, INSA Rennes, CNRS, IETR-UMR 6164, Rennes, France
1 shared publicationLu Zhang
Univ Rennes, INSA Rennes, CNRS, IETR-UMR 6164, Rennes, France
1 shared publicationLuce Morin
Univ Rennes, INSA Rennes, CNRS, IETR-UMR 6164, Rennes, France
1 shared publication
Latest Publications
- Open Access
- 18 September 2024
- Published by Springer Nature in EURASIP Journal on Image and Video Processing
- Vol. 2024 (1) , 1-23
Advanced fine-tuning procedures to enhance DNN robustness in visual coding for machines
Video Coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors. This work complements the MPEG/JVET standardization efforts in improving the resilience of deep neural network (DNN)-based machine models against such coding artifacts by proposing the following three advanced fine-tuning procedures for their training: (1) the progressive increase of the distortion strength as the training proceeds; (2) the incorporation of a regularization term in the original loss function to minimize the distance between predictions on compressed and original content; and (3) a joint training procedure that combines the proposed two approaches. These proposals were evaluated against a conventional fine-tuning anchor on two different machine tasks and datasets: image classification on ImageNet and semantic segmentation on Cityscapes. Our joint training procedure is shown to reduce the training time in both cases and still obtain a 2.4% coding gain in image classification and 7.4% in semantic segmentation, whereas a slight increase in training time can bring up to 9.4% better coding efficiency for the segmentation. All these coding gains are obtained without any additional inference or encoding time. As these advanced fine-tuning procedures are standard-compliant, they offer the potential to have a significant impact on visual coding for machine applications.
- 18 September 2024
- Published by Springer Nature in EURASIP Journal on Image and Video Processing
- Vol. 2024 (1) , 1-23
Open AccessAdvanced fine-tuning procedures to enhance DNN robustness in visual coding for machines
Video Coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors. This work complements the MPEG/JVET standardization efforts in improving the resilience of deep neural network (DNN)-based machine models against such coding artifacts by proposing the following three advanced fine-tuning procedures for their training: (1) the progressive increase of the distortion strength as the training proceeds; (2) the incorporation of a regularization term in the original loss function to minimize the distance between predictions on compressed and original content; and (3) a joint training procedure that combines the proposed two approaches. These proposals were evaluated against a conventional fine-tuning anchor on two different machine tasks and datasets: image classification on ImageNet and semantic segmentation on Cityscapes. Our joint training procedure is shown to reduce the training time in both cases and still obtain a 2.4% coding gain in image classification and 7.4% in semantic segmentation, whereas a slight increase in training time can bring up to 9.4% better coding efficiency for the segmentation. All these coding gains are obtained without any additional inference or encoding time. As these advanced fine-tuning procedures are standard-compliant, they offer the potential to have a significant impact on visual coding for machine applications.
- Open Access
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1570-1574
Rate-Distortion Optimized Motion Estimation for on-the-Sphere Compression of 360 Videos
On-the-sphere compression of omnidirectional videos is a very promising approach. First, it saves computational complexity as it avoids to project the sphere onto a 2D map, as classically done. Second, and more importantly, it allows to achieve a better rate-distortion tradeoff, since neither the visual data nor its domain of definition are distorted. In this paper, the on-the-sphere compression [1] for omnidirectional still images is extended to videos. We first propose a complete review of existing spherical motion models. Then we pro-pose a new one called tangent-linear+t. We finally propose a rate-distortion optimized algorithm to locally choose the best motion model for efficient motion estimation/compensation. For that purpose, we additionally propose a finer search pattern, called spherical-uniform, for the motion parameters, which leads to a more accurate block prediction. The novel algorithm leads to rate-distortion gains compared to methods based on a unique motion model.
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1570-1574
Open AccessRate-Distortion Optimized Motion Estimation for on-the-Sphere Compression of 360 Videos
On-the-sphere compression of omnidirectional videos is a very promising approach. First, it saves computational complexity as it avoids to project the sphere onto a 2D map, as classically done. Second, and more importantly, it allows to achieve a better rate-distortion tradeoff, since neither the visual data nor its domain of definition are distorted. In this paper, the on-the-sphere compression [1] for omnidirectional still images is extended to videos. We first propose a complete review of existing spherical motion models. Then we pro-pose a new one called tangent-linear+t. We finally propose a rate-distortion optimized algorithm to locally choose the best motion model for efficient motion estimation/compensation. For that purpose, we additionally propose a finer search pattern, called spherical-uniform, for the motion parameters, which leads to a more accurate block prediction. The novel algorithm leads to rate-distortion gains compared to methods based on a unique motion model.