no code implementations • 14 Feb 2024 • Jie Mei, Mingyuan Jiu, Hichem Sahbi, Xiaoheng Jiang, Mingliang Xu
Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data.
no code implementations • 29 Dec 2023 • Hichem Sahbi
In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and weights.
no code implementations • 28 Dec 2023 • Hichem Sahbi
Then, we further explore the potential of this objective function, by considering a reinforcement learning approach that finds the best combination of diversity, representativity and uncertainty as well as display-sizes through active learning iterations, leading to better generalization as shown through experiments in interactive satellite image change detection.
1 code implementation • 10 Nov 2023 • Remi Marsal Florian Chabot, Angelique Loesch, William Grolleau, Hichem Sahbi
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis.
no code implementations • 26 Sep 2023 • Hichem Sahbi, Sebastien Deschamps
The main contribution resides in a novel adversarial model that allows learning the most representative, diverse and uncertain virtual exemplars (as inverted preimages of the trained DNNs) that challenge (the most) the trained DNNs, and this leads to a better re-estimate of these networks in the subsequent iterations of active learning.
no code implementations • 30 Jun 2023 • Hichem Sahbi
This method is known to be successful, but under very high pruning regimes, it suffers from topological inconsistency which renders the extracted subnetworks disconnected, and this hinders their generalization ability.
no code implementations • 30 May 2023 • Hichem Sahbi
Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.
no code implementations • 28 Dec 2022 • Hichem Sahbi, Sebastien Deschamps
Our method is interactive and relies on a question and answer model which asks the oracle (user) questions about the most informative display (dubbed as virtual exemplars), and according to the user's responses, updates change detections.
no code implementations • 19 Dec 2022 • Hichem Sahbi
In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs).
no code implementations • 9 Dec 2022 • Sebastien Deschamps, Hichem Sahbi
The proposed approach is probabilistic and unifies all these criteria in a single objective function whose solution models the probability of relevance of samples (i. e., how critical) when learning a decision function.
no code implementations • 25 Mar 2022 • Hichem Sahbi
Experiments conducted on the challenging FPHA dataset show the substantial gain of our topologically consistent pruning method especially at very high pruning regimes.
no code implementations • 22 Mar 2022 • Hichem Sahbi, Sebastien Deschamps
In this paper, we devise a novel interactive satellite image change detection algorithm based on active learning.
no code implementations • 22 Mar 2022 • Sebastien Deschamps, Hichem Sahbi
To further explore the potential of this objective function, we consider a reinforcement learning approach that finds the best combination of diversity, representativity and uncertainty, through active learning iterations, leading to better generalization as corroborated through experiments in interactive satellite image change detection.
1 code implementation • 25 Feb 2022 • Robin Dupont, Mohammed Amine Alaoui, Hichem Sahbi, Alice Lebois
Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of weights in a network.
no code implementations • 6 Dec 2021 • Hichem Sahbi
Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing convolutional operations to arbitrary non-regular domains.
no code implementations • 22 Nov 2021 • Hichem Sahbi, Haoming Zhan
An intermediate class of methods, based on dynamic networks, has been proposed in the literature and provides a reasonable balance between task memorization and computational footprint.
no code implementations • 8 Oct 2021 • Hichem Sahbi, Sebastien Deschamps, Andrei Stoian
We introduce in this paper a novel active learning algorithm for satellite image change detection.
no code implementations • 8 Jul 2021 • Robin Dupont, Hichem Sahbi, Guillaume Michel
In this paper, we introduce an "end-to-end" lightweight network design that achieves training and pruning simultaneously without fine-tuning.
no code implementations • 12 Apr 2021 • Hichem Sahbi
Spectral graph convolutional networks (GCNs) are particular deep models which aim at extending neural networks to arbitrary irregular domains.
no code implementations • 9 Apr 2021 • Hichem Sahbi
In this paper, we introduce a novel method that learns the topology (or connectivity) of input graphs as a part of GCN design.
no code implementations • 28 Dec 2020 • Hichem Sahbi
The latter makes it possible to design, via implicit kernel representations, convolutional graph filters in a high dimensional and more discriminating space without increasing the number of training parameters.
no code implementations • 21 Dec 2020 • Mingyuan Jiu, Hichem Sahbi
Context modeling is one of the most fertile subfields of visual recognition which aims at designing discriminant image representations while incorporating their intrinsic and extrinsic relationships.
no code implementations • 26 Jun 2020 • Mingyuan Jiu, Hichem Sahbi
Deep kernel map networks have shown excellent performances in various classification problems including image annotation.
no code implementations • 8 Jun 2020 • Ahmed Mazari, Hichem Sahbi
While convolutional and fully connected operations have been widely studied in the literature, the design of pooling operations that handle action recognition, with different sources of temporal granularity in action categories, has comparatively received less attention, and existing solutions rely mainly on max or averaging operations.
no code implementations • 8 Jun 2020 • Ahmed Mazari, Hichem Sahbi
In this paper, we introduce a novel hierarchical aggregation design that captures different levels of temporal granularity in action recognition.
no code implementations • 29 Dec 2019 • Mingyuan Jiu, Hichem Sahbi
This architecture is fully determined by the solution of an objective function mixing a content term that captures the intrinsic similarity between data, a context criterion which models their structure and a regularization term that helps designing smooth kernel network representations.
no code implementations • 12 Dec 2019 • Hichem Sahbi
In this paper, we relax this constraint and allow the support vectors to be learned (instead of being fixed/taken from training data) in order to better fit a given classification task.
no code implementations • 15 Oct 2019 • Ahmed Mazari, Hichem Sahbi
The main contribution of this method resides in a new design principle that learns graph-laplacians as convex combinations of other elementary laplacians each one dedicated to a particular topology of the input graphs.
no code implementations • 30th British Machine Vision Conference 2019 • Ahmed Mazari, Hichem Sahbi
We also introduce a novel pooling operator, on graphs, that proceeds in two steps: context-dependent node expansion is achieved, followed by a global average pooling; the strength of this two-step process resides in its ability to preserve the discrimination power of nodes while achieving permutation invariance.
Ranked #2 on Skeleton Based Action Recognition on SBU
no code implementations • 2 May 2019 • Ahmed Mazari, Hichem Sahbi
Our solution is based on a tree-structured temporal pyramid that aggregates outputs of CNNs at different levels.
no code implementations • 27 Dec 2018 • Hichem Sahbi
We introduce in this work a novel stochastic inference process, for scene annotation and object class segmentation, based on finite state machines (FSMs).
no code implementations • 21 Dec 2018 • Hichem Sahbi
Canonical correlation analysis (CCA) is a statistical learning method that seeks to build view-independent latent representations from multi-view data.
no code implementations • 21 Dec 2018 • Hichem Sahbi
The design principle of these reduced complexity networks is based on a variant of the cross-entropy criterion that reduces the complexity of the networks in the cascade while preserving all the positive responses of the original kernel network.
no code implementations • 30 Apr 2018 • Mingyuan Jiu, Hichem Sahbi
This scheme has proven to be effective, but intractable when handling large-scale datasets especially when the depth of the trained networks increases; indeed, the complexity of evaluating these networks scales quadratically w. r. t.
no code implementations • 23 Mar 2018 • Mingyuan Jiu, Hichem Sahbi
We apply this context and kernel learning framework to image classification using the challenging ImageCLEF Photo Annotation benchmark; the latter shows that our deep context learning provides highly effective kernels for image classification as corroborated through extensive experiments.
no code implementations • 28 Feb 2018 • Anjan Dutta, Hichem Sahbi
In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision.
BIG-bench Machine Learning Vocal Bursts Intensity Prediction
1 code implementation • 1 Feb 2017 • Anjan Dutta, Hichem Sahbi
In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision.