References of "Aouada, Djamila 50000437"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailCalcGraph: taming the high costs of deep learning using models
Lorentz, Joe UL; Hartmann, Thomas UL; Moawad, Assaad UL et al

in Software and Systems Modeling (2022)

Models based on differential programming, like deep neural networks, are well established in research and able to outperform manually coded counterparts in many applications. Today, there is a rising ... [more ▼]

Models based on differential programming, like deep neural networks, are well established in research and able to outperform manually coded counterparts in many applications. Today, there is a rising interest to introduce this flexible modeling to solve real-world problems. A major challenge when moving from research to application is the strict constraints on computational resources (memory and time). It is difficult to determine and contain the resource requirements of differential models, especially during the early training and hyperparameter exploration stages. In this article, we address this challenge by introducing CalcGraph, a model abstraction of differentiable programming layers. CalcGraph allows to model the computational resources that should be used and then CalcGraph’s model interpreter can automatically schedule the execution respecting the specifications made. We propose a novel way to efficiently switch models from storage to preallocated memory zones and vice versa to maximize the number of model executions given the available resources. We demonstrate the efficiency of our approach by showing that it consumes less resources than state-of-the-art frameworks like TensorFlow and PyTorch for single-model and multi-model execution. [less ▲]

Detailed reference viewed: 25 (1 UL)
Full Text
See detailPose Estimation of a Known Texture-Less Space Target using Convolutional Neural Networks
Rathinam, Arunkumar UL; Gaudilliere, Vincent UL; Pauly, Leo UL et al

in 73rd International Astronautical Congress, Paris 18-22 September 2022 (2022, September)

Orbital debris removal and On-orbit Servicing, Assembly and Manufacturing [OSAM] are the main areas for future robotic space missions. To achieve intelligence and autonomy in these missions and to carry ... [more ▼]

Orbital debris removal and On-orbit Servicing, Assembly and Manufacturing [OSAM] are the main areas for future robotic space missions. To achieve intelligence and autonomy in these missions and to carry out robot operations, it is essential to have autonomous guidance and navigation, especially vision-based navigation. With recent advances in machine learning, the state-of-the-art Deep Learning [DL] approaches for object detection, and camera pose estimation have advanced to be on par with classical approaches and can be used for target pose estimation during relative navigation scenarios. The state-of-the-art DL-based spacecraft pose estimation approaches are suitable for any known target with significant surface textures. However, it is less applicable in a scenario where the target is a texture-less and symmetric object like rocket nozzles. This paper investigates a novel ellipsoid-based approach combined with convolutional neural networks for texture-less space object pose estimation. Also, this paper presents the dataset for a new texture-less space target, an apogee kick motor, which is used for the study. It includes the synthetic images generated from the simulator developed for rendering synthetic space imagery. [less ▲]

Detailed reference viewed: 68 (5 UL)
Full Text
Peer Reviewed
See detailProfiling the real world potential of neural network compression
Lorentz, Joe UL; Hartmann, Thomas; Moawad, Assaad et al

in 2022 IEEE International Conference on Omni-layer Intelligent Systems (COINS), Barcelona 1-3 August 2022 (2022, August 01)

Abstract—Many real world computer vision applications are required to run on hardware with limited computing power, often referred to as ”edge devices”. The state of the art in computer vision continues ... [more ▼]

Abstract—Many real world computer vision applications are required to run on hardware with limited computing power, often referred to as ”edge devices”. The state of the art in computer vision continues towards ever bigger and deeper neural networks with equally rising computational requirements. Model compression methods promise to substantially reduce the computation time and memory demands with little to no impact on the model robustness. However, evaluation of the compression is mostly based on theoretic speedups in terms of required floating-point operations. This work offers a tool to profile the actual speedup offered by several compression algorithms. Our results show a significant discrepancy between the theoretical and actual speedup on various hardware setups. Furthermore, we show the potential of model compressions and highlight the importance of selecting the right compression algorithm for a target task and hardware. The code to reproduce our experiments is available at https://hub.datathings.com/papers/2022-coins. [less ▲]

Detailed reference viewed: 19 (3 UL)
Full Text
Peer Reviewed
See detailFace-GCN: A Graph Convolutional Network for 3D Dynamic Face Recognition
Papadopoulos, Konstantinos; Kacem, Anis UL; Shabayek, Abdelrahman et al

in 2022 8th International Conference on Virtual Reality (2022)

Face recognition has significantly advanced over the past years. However, most of the proposed approaches rely on static RGB frames and on neutral facial expressions. This has two disadvantages. First ... [more ▼]

Face recognition has significantly advanced over the past years. However, most of the proposed approaches rely on static RGB frames and on neutral facial expressions. This has two disadvantages. First, important facial shape cues are ignored. Second, facial deformations due to expressions can have an impact in the performance of such a method. In this paper, we propose a novel framework for dynamic 3D face recognition based on facial keypoints. Each dynamic sequence of facial expressions is represented as a spatio-temporal graph, which is constructed using 3D facial landmarks. Each graph node contains local shape and texture features that are extracted from its neighborhood. For the classification of face videos, a Spatio-temporal Graph Convolutional Network (ST-GCN) is used. Finally, we evaluate our approach on a challenging dynamic 3D facial expression dataset. [less ▲]

Detailed reference viewed: 64 (6 UL)
Full Text
Peer Reviewed
See detailDisentangled Face Identity Representationsfor Joint 3D Face Recognition and Neutralisation
Kacem, Anis UL; cherenkova, kseniya; Aouada, Djamila UL

in 2022 8th International Conference on Virtual Reality (2022)

In this paper, we propose a new deep learning based approach for disentangling face identity representations from expressive 3D faces. Given a 3D face, our approach not only extracts a disentangled ... [more ▼]

In this paper, we propose a new deep learning based approach for disentangling face identity representations from expressive 3D faces. Given a 3D face, our approach not only extracts a disentangled identity representation, but also generates a realistic 3D face with a neutral expression while predicting its identity. The proposed network consists of three components; (1) a Graph Convolutional Autoencoder (GCA) to encode the 3D faces into latent representations, (2) a Generative Adversarial Network (GAN) that translates the latent representations of expressive faces into those of neutral faces, (3) and an identity recognition sub-network taking advantage of the neutralized latent representations for 3D face recognition. The whole network is trained in an end-to-end manner. Experiments are conducted on three publicly available datasets showing the effectiveness of the proposed approach. [less ▲]

Detailed reference viewed: 74 (15 UL)
Full Text
Peer Reviewed
See detailIML-GCN: Improved Multi-Label Graph Convolutional Network for Efficient yet Precise Image Classification
Singh, Inder Pal UL; Oyedotun, Oyebade UL; Ghorbel, Enjie UL et al

in AAAI-22 Workshop Program-Deep Learning on Graphs: Methods and Applications (2022, February)

In this paper, we propose the Improved Multi-Label Graph Convolutional Network (IML-GCN) as a precise and efficient framework for multi-label image classification. Although previous approaches have shown ... [more ▼]

In this paper, we propose the Improved Multi-Label Graph Convolutional Network (IML-GCN) as a precise and efficient framework for multi-label image classification. Although previous approaches have shown great performance, they usually make use of very large architectures. To handle this, we propose to combine the small version of a newly introduced network called TResNet with an extended version of Multi-label Graph Convolution Networks (ML-GCN); therefore ensuring the learning of label correlation while reducing the size of the overall network. The proposed approach considers a novel image feature embedding instead of using word embeddings. In fact, the latter are learned from words and not images making them inadequate for the task of multi-label image classification. Experimental results show that our framework competes with the state-of-the-art on two multi-label image benchmarks in terms of both precision and memory requirements. [less ▲]

Detailed reference viewed: 249 (20 UL)
Full Text
Peer Reviewed
See detailCubeSat-CDT: A Cross-Domain Dataset for 6-DoF Trajectory Estimation of a Symmetric Spacecraft
Mohamed Ali, Mohamed Adel UL; Rathinam, Arunkumar UL; Gaudilliere, Vincent UL et al

in Proceedings of the 17th European Conference on Computer Vision Workshops (ECCVW 2022) (2022)

This paper introduces a new cross-domain dataset, CubeSat- CDT, that includes 21 trajectories of a real CubeSat acquired in a labora- tory setup, combined with 65 trajectories generated using two ... [more ▼]

This paper introduces a new cross-domain dataset, CubeSat- CDT, that includes 21 trajectories of a real CubeSat acquired in a labora- tory setup, combined with 65 trajectories generated using two rendering engines – i.e. Unity and Blender. The three data sources incorporate the same 1U CubeSat and share the same camera intrinsic parameters. In ad- dition, we conduct experiments to show the characteristics of the dataset using a novel and efficient spacecraft trajectory estimation method, that leverages the information provided from the three data domains. Given a video input of a target spacecraft, the proposed end-to-end approach re- lies on a Temporal Convolutional Network that enforces the inter-frame coherence of the estimated 6-Degree-of-Freedom spacecraft poses. The pipeline is decomposed into two stages; first, spatial features are ex- tracted from each frame in parallel; second, these features are lifted to the space of camera poses while preserving temporal information. Our re- sults highlight the importance of addressing the domain gap problem to propose reliable solutions for close-range autonomous relative navigation between spacecrafts. Since the nature of the data used during training impacts directly the performance of the final solution, the CubeSat-CDT dataset is provided to advance research into this direction. [less ▲]

Detailed reference viewed: 64 (11 UL)
Full Text
Peer Reviewed
See detailMULTI LABEL IMAGE CLASSIFICATION USING ADAPTIVE GRAPH CONVOLUTIONAL NETWORKS (ML-AGCN)
Singh, Inder Pal UL; Ghorbel, Enjie UL; Oyedotun, Oyebade UL et al

in IEEE International Conference on Image Processing (2022)

In this paper, a novel graph-based approach for multi-label image classification called Multi-Label Adaptive Graph Convolutional Network (ML-AGCN) is introduced. Graph-based methods have shown great ... [more ▼]

In this paper, a novel graph-based approach for multi-label image classification called Multi-Label Adaptive Graph Convolutional Network (ML-AGCN) is introduced. Graph-based methods have shown great potential in the field of multi-label classification. However, these approaches heuristically fix the graph topology for modeling label dependencies, which might be not optimal. To handle that, we propose to learn the topology in an end-to-end manner. Specifically, we incorporate an attention-based mechanism for estimating the pairwise importance between graph nodes and a similarity-based mechanism for conserving the feature similarity between different nodes. This offers a more flexible way for adaptively modeling the graph. Experimental results are reported on two well-known datasets, namely, MS-COCO and VG-500. Results show that ML-AGCN outperforms state-of-the-art methods while reducing the number of model parameters. [less ▲]

Detailed reference viewed: 79 (5 UL)
Full Text
Peer Reviewed
See detailTSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network
Karadeniz, Ahmet Serdar UL; Ali, Sk Aziz UL; Kacem, Anis UL et al

in Karadeniz, Ahmet Serdar; Ali, Sk Aziz; Kacem, Anis (Eds.) et al TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network (2022)

Reconstructing 3D human body shapes from 3D partial textured scans remains a fundamental task for many computer vision and graphics applications – e.g., body animation, and virtual dressing. We propose a ... [more ▼]

Reconstructing 3D human body shapes from 3D partial textured scans remains a fundamental task for many computer vision and graphics applications – e.g., body animation, and virtual dressing. We propose a new neural network architecture for 3D body shape and highresolution texture completion – TSCom-Net – that can reconstruct the full geometry from mid-level to high-level partial input scans. We decompose the overall reconstruction task into two stages – first, a joint implicit learning network (SCom-Net and TCom-Net) that takes a voxelized scan and its occupancy grid as input to reconstruct the full body shape and predict vertex textures. Second, a high-resolution texture completion network, that utilizes the predicted coarse vertex textures to inpaint the missing parts of the partial ‘texture atlas’. A Thorough experimental evaluation on 3DBodyTex.V2 dataset shows that our method achieves competitive results with respect to the state-of-the-art while generalizing to different types and levels of partial shapes. The proposed method has also ranked second in the track1 of SHApe Recovery from Partial textured 3D scans (SHARP [37 , 2]) 2022 1 challenge1. [less ▲]

Detailed reference viewed: 57 (12 UL)
Full Text
Peer Reviewed
See detailLeveraging Equivariant Features for Absolute Pose Regression
Mohamed Ali, Mohamed Adel UL; Gaudilliere, Vincent UL; Ortiz Del Castillo, Miguel UL et al

in IEEE Conference on Computer Vision and Pattern Recognition. (2022)

Pose estimation enables vision-based systems to refer to their environment, supporting activities ranging from scene navigation to object manipulation. However, end-to-end approaches, that have achieved ... [more ▼]

Pose estimation enables vision-based systems to refer to their environment, supporting activities ranging from scene navigation to object manipulation. However, end-to-end approaches, that have achieved state-of-the-art performance in many perception tasks, are still unable to compete with 3D geometry-based methods in pose estimation. Indeed, absolute pose regression has been proven to be more related to image retrieval than to 3D structure. Our assumption is that statistical features learned by classical convolutional neural networks do not carry enough geometrical information for reliably solving this task. This paper studies the use of deep equivariant features for end-to-end pose regression. We further propose a translation and rotation equivariant Convolutional Neural Network whose architecture directly induces representations of camera motions into the feature space. In the context of absolute pose regression, this geometric property allows for implicitly augmenting the training data under a whole group of image plane-preserving transformations. Therefore, directly learning equivariant features efficiently compensates for learning intermediate representations that are indirectly equivariant yet data-intensive. Extensive experimental validation demonstrates that our lightweight model outperforms existing ones on standard datasets. [less ▲]

Detailed reference viewed: 83 (0 UL)
Full Text
Peer Reviewed
See detailWhy is Everyone Training Very Deep Neural Network with Skip Connections?
Oyedotun, Oyebade UL; Al Ismaeil, Kassem; Aouada, Djamila UL

in IEEE Transactions on Neural Networks and Learning Systems (2021)

Detailed reference viewed: 49 (6 UL)
Full Text
Peer Reviewed
See detailLeveraging High-Frequency Components for Deepfake Detection
Mejri, Nesryne UL; Papadopoulos, Konstantinos UL; Aouada, Djamila UL

in IEEE Workshop on Multimedia Signal Processing (2021)

In the past years, RGB-based deepfake detection has shown notable progress thanks to the development of effective deep neural networks. However, the performance of deepfake detectors remains primarily ... [more ▼]

In the past years, RGB-based deepfake detection has shown notable progress thanks to the development of effective deep neural networks. However, the performance of deepfake detectors remains primarily dependent on the quality of the forged content and the level of artifacts introduced by the forgery method. To detect these artifacts, it is often necessary to separate and analyze the frequency components of an image. In this context, we propose to utilize the high-frequency components of color images by introducing an end-to-end trainable module that (a) extracts features from high-frequency components and (b) fuses them with the features of the RGB input. The module not only exploits the high-frequency anomalies present in manipulated images but also can be used with most RGB-based deepfake detectors. Experimental results show that the proposed approach boosts the performance of state-of-the-art networks, such as XceptionNet and EfficientNet, on a challenging deepfake dataset. [less ▲]

Detailed reference viewed: 236 (69 UL)
Full Text
Peer Reviewed
See detailLeveraging Temporal Information for 3D Trajectory Estimation of Space Objects
Mohamed Ali, Mohamed Adel UL; Ortiz Del Castillo, Miguel UL; Al Ismaeil, Kassem UL et al

in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops (2021, October)

Detailed reference viewed: 73 (24 UL)
Full Text
Peer Reviewed
See detailExplaining Defect Detection with Saliency Maps
Lorentz, Joe UL; Hartmann, Thomas; Moawad, Assaad et al

in 34th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2021, Kuala Lumpur, Malaysia, July 26–29, 2021, Proceedings, Part II (2021, July 19)

The rising quality and throughput demands of the manufacturing domain require flexible, accurate and explainable computer-vision solutions for defect detection. Deep Neural Networks (DNNs) reach state-of ... [more ▼]

The rising quality and throughput demands of the manufacturing domain require flexible, accurate and explainable computer-vision solutions for defect detection. Deep Neural Networks (DNNs) reach state-of-the-art performance on various computer-vision tasks but wide-spread application in the industrial domain is blocked by the lacking explainability of DNN decisions. A promising, human-readable solution is given by saliency maps, heatmaps highlighting the image areas that influence the classifier’s decision. This work evaluates a selection of saliency methods in the area of industrial quality assurance. To this end we propose the distance pointing game, a new metric to quantify the meaningfulness of saliency maps for defect detection. We provide steps to prepare a publicly available dataset on defective steel plates for the proposed metric. Additionally, the computational complexity is investigated to determine which methods could be integrated on industrial edge devices. Our results show that DeepLift, GradCAM and GradCAM++ outperform the alternatives while the computational cost is feasible for real time applications even on edge devices. This indicates that the respective methods could be used as an additional, autonomous post-classification step to explain decisions taken by intelligent quality assurance systems. [less ▲]

Detailed reference viewed: 86 (19 UL)
Full Text
Peer Reviewed
See detailLSPnet: A 2D Localization-oriented Spacecraft Pose Estimation Neural Network
Garcia Sanchez, Albert UL; Mohamed Ali, Mohamed Adel UL; Gaudilliere, Vincent UL et al

in Proceedings of Conference on Computer Vision and Pattern Recognition Workshops (2021, June)

Being capable of estimating the pose of uncooperative objects in space has been proposed as a key asset for enabling safe close-proximity operations such as space rendezvous, in-orbit servicing and active ... [more ▼]

Being capable of estimating the pose of uncooperative objects in space has been proposed as a key asset for enabling safe close-proximity operations such as space rendezvous, in-orbit servicing and active debris removal. Usual approaches for pose estimation involve classical computer vision-based solutions or the application of Deep Learning (DL) techniques. This work explores a novel DL-based methodology, using Convolutional Neural Networks (CNNs), for estimating the pose of uncooperative spacecrafts. Contrary to other approaches, the proposed CNN directly regresses poses without needing any prior 3D information. Moreover, bounding boxes of the spacecraft in the image are predicted in a simple, yet efficient manner. The performed experiments show how this work competes with the state-of-the-art in uncooperative spacecraft pose estimation, including works which require 3D information as well as works which predict bounding boxes through sophisticated CNNs. [less ▲]

Detailed reference viewed: 251 (34 UL)
Full Text
Peer Reviewed
See detailVertex Feature Encoding and Hierarchical Temporal Modeling in a Spatio-Temporal Graph Convolutional Network for Action Recognition
Papadopoulos, Konstantinos UL; Ghorbel, Enjie UL; Aouada, Djamila UL et al

in International Conference on Pattern Recognition, Milan 10-15 January 2021 (2021)

Detailed reference viewed: 147 (28 UL)