Sébastien Adam
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
Research Subjects
Sébastien Adam has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Clément Chatelain
INSA of Rouen Normandy
4 shared publications Eric Trupin
Rouen University
2 shared publications- Pierre Héroux
Université de Rouen - LITIS EA 4108, BP 12, 76801 Saint-Etienne du Rouvray, France
2 shared publications - Romain Hérault
Normandie University, INSA Rouen, LITIS, Rouen, France
2 shared publications - Soufiane Belharbi
Normandie Univ UNIROUEN UNIHAVRE, INSA Rouen 76000 Rouen LITIS France
2 shared publications - Adam Winstanley
National University of Ireland Maynooth
1 shared publication
Latest Publications
- Open Access
Temporal receptive field in dynamic graph learning: A comprehensive analysis
Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .
Open AccessTemporal receptive field in dynamic graph learning: A comprehensive analysis
Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .
- Open Access
Neural Networks Regularization Through Class-wise Invariant Representation Learning
Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by proposing a new regularization term that constrains the hidden layers of a network to learn class-wise invariant representations. In our regularization framework, learning invariant representations is generalized to the class membership where samples with the same class should have the same representation. Numerical experiments over MNIST and its variants showed that our proposal helps improving the generalization of neural network particularly when trained with few samples. We provide the source code of our framework https://github.com/sbelharbi/learning-class-invariant-features .
Open AccessNeural Networks Regularization Through Class-wise Invariant Representation Learning
Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by proposing a new regularization term that constrains the hidden layers of a network to learn class-wise invariant representations. In our regularization framework, learning invariant representations is generalized to the class membership where samples with the same class should have the same representation. Numerical experiments over MNIST and its variants showed that our proposal helps improving the generalization of neural network particularly when trained with few samples. We provide the source code of our framework https://github.com/sbelharbi/learning-class-invariant-features .
- Open Access
Deep Neural Networks Regularization for Structured Output Prediction
A deep neural network model is a powerful framework for learning representations. Usually, it is used to learn the relation $x \to y$ by exploiting the regularities in the input $x$. In structured output prediction problems, $y$ is multi-dimensional and structural relations often exist between the dimensions. The motivation of this work is to learn the output dependencies that may lie in the output data in order to improve the prediction accuracy. Unfortunately, feedforward networks are unable to exploit the relations between the outputs. In order to overcome this issue, we propose in this paper a regularization scheme for training neural networks for these particular tasks using a multi-task framework. Our scheme aims at incorporating the learning of the output representation $y$ in the training process in an unsupervised fashion while learning the supervised mapping function $x \to y$. We evaluate our framework on a facial landmark detection problem which is a typical structured output task. We show over two public challenging datasets (LFPW and HELEN) that our regularization scheme improves the generalization of deep neural networks and accelerates their training. The use of unlabeled data and label-only data is also explored, showing an additional improvement of the results. We provide an opensource implementation (https://github.com/sbelharbi/structured-output-ae) of our framework.Open AccessDeep Neural Networks Regularization for Structured Output Prediction
A deep neural network model is a powerful framework for learning representations. Usually, it is used to learn the relation $x \to y$ by exploiting the regularities in the input $x$. In structured output prediction problems, $y$ is multi-dimensional and structural relations often exist between the dimensions. The motivation of this work is to learn the output dependencies that may lie in the output data in order to improve the prediction accuracy. Unfortunately, feedforward networks are unable to exploit the relations between the outputs. In order to overcome this issue, we propose in this paper a regularization scheme for training neural networks for these particular tasks using a multi-task framework. Our scheme aims at incorporating the learning of the output representation $y$ in the training process in an unsupervised fashion while learning the supervised mapping function $x \to y$. We evaluate our framework on a facial landmark detection problem which is a typical structured output task. We show over two public challenging datasets (LFPW and HELEN) that our regularization scheme improves the generalization of deep neural networks and accelerates their training. The use of unlabeled data and label-only data is also explored, showing an additional improvement of the results. We provide an opensource implementation (https://github.com/sbelharbi/structured-output-ae) of our framework. - 1 August 2017
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 87, 95-103
Spotting L3 slice in CT scans using deep convolutional network and transfer learning
- 1 August 2017
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 87, 95-103
Spotting L3 slice in CT scans using deep convolutional network and transfer learning
- 5 November 2016
- Published by Springer Nature
- p. 485-495
Exact Graph Edit Distance Computation Using a Binary Linear Program
- 5 November 2016
- Published by Springer Nature
- p. 485-495
Exact Graph Edit Distance Computation Using a Binary Linear Program
- 31 July 2011
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 115 (7) , 905-918
Learning graph prototypes for shape recognition
- 31 July 2011
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 115 (7) , 905-918
Learning graph prototypes for shape recognition
- 18 November 2006
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 9 (1) , 59-74
A general framework for the evaluation of symbol recognition methods
- 18 November 2006
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 9 (1) , 59-74
A general framework for the evaluation of symbol recognition methods
- 1 January 2005
- Published by INSTICC
- p. 164-174
Indexation of Document Images Using Frequent Items