Gauthier Tallec
Research Subjects
Research Interests
Gauthier Tallec has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Kevin Bailly
Datakalab,Paris,France,75017
4 shared publications - Arnaud Dapogny
Datakalab, Paris, France
3 shared publications - Jules Bonnard
Sorbonne Université, CNRS, ISIR
3 shared publications Edouard Yvinec
Datakalab,Paris,France,75017
2 shared publicationsAatish Pradhan
1 shared publication- Aditya Sonpal
North Carolina State University
1 shared publication
Latest Publications
- Open Access
- 5 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
RULe: Relocalization-Uniformization-Landmark Estimation Network for Real-Time Face Alignment in Degraded Conditions
Face alignment refers to the process of estimating the position of a number of salient landmarks on face images or videos, such as mouth and eye corners, nose tip, etc. With the availability of large annotated databases and the rise of deep learning-based methods, face alignment as a domain has matured to a point where it can be applied in more or less unconstrained conditions, e.g. non-frontal head poses, presence of heavy make-up or partial occlusions. However, when considering real-case alignment on videos with possibly low frame rates, we need to make sure that the algorithms are robust to jittering of the face bounding box localization, low-resolution of the face crops, possible bad environmental lighting, brightness, and presence of noise. To tackle these issues, we propose RULe, a three-staged Relocalization-Uniformization-Landmark Estimation network. In the first stage, an initial loosely localized bounding box gets refined to output a well centered face crop, thus reducing the variability of the images prior to passing them to the subsequent stage. Then, in the second stage, the face style is uniformized (using adversarial learning as well as perceptual losses) to correct low resolution or variations of brightness/contrast. Finally, the third stage outputs a precise landmark estimation given such enhanced face crop using a cascaded compact model trained using hint-based knowledge distillation. We show through a variety of experiments that RULe achieves real-time face alignment with state-of-the-art precision in heavily degraded conditions.
- 5 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Open AccessRULe: Relocalization-Uniformization-Landmark Estimation Network for Real-Time Face Alignment in Degraded Conditions
Face alignment refers to the process of estimating the position of a number of salient landmarks on face images or videos, such as mouth and eye corners, nose tip, etc. With the availability of large annotated databases and the rise of deep learning-based methods, face alignment as a domain has matured to a point where it can be applied in more or less unconstrained conditions, e.g. non-frontal head poses, presence of heavy make-up or partial occlusions. However, when considering real-case alignment on videos with possibly low frame rates, we need to make sure that the algorithms are robust to jittering of the face bounding box localization, low-resolution of the face crops, possible bad environmental lighting, brightness, and presence of noise. To tackle these issues, we propose RULe, a three-staged Relocalization-Uniformization-Landmark Estimation network. In the first stage, an initial loosely localized bounding box gets refined to output a well centered face crop, thus reducing the variability of the images prior to passing them to the subsequent stage. Then, in the second stage, the face style is uniformized (using adversarial learning as well as perceptual losses) to correct low resolution or variations of brightness/contrast. Finally, the third stage outputs a precise landmark estimation given such enhanced face crop using a cascaded compact model trained using hint-based knowledge distillation. We show through a variety of experiments that RULe achieves real-time face alignment with state-of-the-art precision in heavily degraded conditions.
- Open Access
- 5 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction
Deep learning-based multi-task approaches usually rely on factorizing representation layers up to a certain point, where the network splits into several heads, each one addressing a specific task. Depending on the inter-task correlation, such naive model may or may not allow the tasks to benefit from each others. In this paper, we propose a novel Semantic Orthogonality Spaces (SOS) method for multi-task problems, where each task is predicted using the information from a common subspace that factorizes information among all tasks, as well as a task-specific subspace. We enforce orthogonality between these tasks by applying soft orthogonality constraints, as well as adversarially-learned semantic orthogonality objectives that ensures that predicting one task requires the specific information related to that task. We demonstrate the effectiveness of SOS on synthetic data, as well as for large-scale facial attributes prediction. In particular, we use SOS to craft a lightweight architecture that provides high-end accuracies on CelebA database.
- 5 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Open AccessAdversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction
Deep learning-based multi-task approaches usually rely on factorizing representation layers up to a certain point, where the network splits into several heads, each one addressing a specific task. Depending on the inter-task correlation, such naive model may or may not allow the tasks to benefit from each others. In this paper, we propose a novel Semantic Orthogonality Spaces (SOS) method for multi-task problems, where each task is predicted using the information from a common subspace that factorizes information among all tasks, as well as a task-specific subspace. We enforce orthogonality between these tasks by applying soft orthogonality constraints, as well as adversarially-learned semantic orthogonality objectives that ensures that predicting one task requires the specific information related to that task. We demonstrate the effectiveness of SOS on synthetic data, as well as for large-scale facial attributes prediction. In particular, we use SOS to craft a lightweight architecture that provides high-end accuracies on CelebA database.
- Open Access
Multi-Task Transformer with uncertainty modelling for Face Based Affective Computing
Face based affective computing consists in detecting emotions from face images. It is useful to unlock better automatic comprehension of human behaviours and could pave the way toward improved human-machines interactions. However it comes with the challenging task of designing a computational representation of emotions. So far, emotions have been represented either continuously in the 2D Valence/Arousal space or in a discrete manner with Ekman's 7 basic emotions. Alternatively, Ekman's Facial Action Unit (AU) system have also been used to caracterize emotions using a codebook of unitary muscular activations. ABAW3 and ABAW4 Multi-Task Challenges are the first work to provide a large scale database annotated with those three types of labels. In this paper we present a transformer based multi-task method for jointly learning to predict valence arousal, action units and basic emotions. From an architectural standpoint our method uses a taskwise token approach to efficiently model the similarities between the tasks. From a learning point of view we use an uncertainty weighted loss for modelling the difference of stochasticity between the three tasks annotations.
Open AccessMulti-Task Transformer with uncertainty modelling for Face Based Affective Computing
Face based affective computing consists in detecting emotions from face images. It is useful to unlock better automatic comprehension of human behaviours and could pave the way toward improved human-machines interactions. However it comes with the challenging task of designing a computational representation of emotions. So far, emotions have been represented either continuously in the 2D Valence/Arousal space or in a discrete manner with Ekman's 7 basic emotions. Alternatively, Ekman's Facial Action Unit (AU) system have also been used to caracterize emotions using a codebook of unitary muscular activations. ABAW3 and ABAW4 Multi-Task Challenges are the first work to provide a large scale database annotated with those three types of labels. In this paper we present a transformer based multi-task method for jointly learning to predict valence arousal, action units and basic emotions. From an architectural standpoint our method uses a taskwise token approach to efficiently model the similarities between the tasks. From a learning point of view we use an uncertainty weighted loss for modelling the difference of stochasticity between the three tasks annotations.
- 2 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (4) , 2876-2888
Multi-Order Networks for Action Unit Detection
Action Units (AU) are muscular activations used to describe facial expressions. Therefore accurate AU recognition unlocks unbiaised face representation which can improve face-based affective computing applications. From a learning standpoint AU detection is a multi-task problem with strong inter-task dependencies. To solve such problem, most approaches either rely on weight sharing, or add explicit dependency modelling by decomposing the joint task distribution using Bayes chain rule. If the latter strategy yields comprehensive inter-task relationships modelling, it requires imposing an arbitrary order into an unordered task set. Crucially, this ordering choice has been identified as a source of performance variations. In this paper, we present Multi-Order Network (MONET), a multi-task method with joint task order optimization. MONET uses a differentiable order selection to jointly learn task-wise modules with their optimal chaining order. Furthermore, we introduce warmup and order dropout to enhance order selection by encouraging order exploration. Experimentally, we first demonstrate MONET capacity to retrieve the optimal order in a toy environment. Second, we validate MONET architecture by showing that MONET outperforms existing multi-task baselines on multiple attribute detection problems chosen for their wide range of dependency settings. More importantly, we demonstrate that MONET significantly extends state-of-the-art performance in AU detection.
- 2 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (4) , 2876-2888
Multi-Order Networks for Action Unit Detection
Action Units (AU) are muscular activations used to describe facial expressions. Therefore accurate AU recognition unlocks unbiaised face representation which can improve face-based affective computing applications. From a learning standpoint AU detection is a multi-task problem with strong inter-task dependencies. To solve such problem, most approaches either rely on weight sharing, or add explicit dependency modelling by decomposing the joint task distribution using Bayes chain rule. If the latter strategy yields comprehensive inter-task relationships modelling, it requires imposing an arbitrary order into an unordered task set. Crucially, this ordering choice has been identified as a source of performance variations. In this paper, we present Multi-Order Network (MONET), a multi-task method with joint task order optimization. MONET uses a differentiable order selection to jointly learn task-wise modules with their optimal chaining order. Furthermore, we introduce warmup and order dropout to enhance order selection by encouraging order exploration. Experimentally, we first demonstrate MONET capacity to retrieve the optimal order in a toy environment. Second, we validate MONET architecture by showing that MONET outperforms existing multi-task baselines on multiple attribute detection problems chosen for their wide range of dependency settings. More importantly, we demonstrate that MONET significantly extends state-of-the-art performance in AU detection.