arXiv subjects

A. Ben Hamza

Publications and source records attributed to A. Ben Hamza.

36 records · Page 2Linked to original sources

arXiv2023

Iterative Graph Filtering Network for 3D Human Pose Estimation

Graph convolutional networks (GCNs) have proven to be an effective approach for 3D human pose estimation. By naturally modeling the skeleton structure of the human body as a graph, GCNs are able to capture the spatial relationships between joints and learn an efficient representation of the underlying pose. However, most GCN-based methods use a shared weight matrix, making it challenging to accurately capture the different and complex relationships between joints. In this paper, we introduce an iterative graph filtering framework for 3D human pose estimation, which aims to predict the 3D joint positions given a set of 2D joint locations in images. Our approach builds upon the idea of iteratively solving graph filtering with Laplacian regularization via the Gauss-Seidel iterative method. Motivated by this iterative solution, we design a Gauss-Seidel network (GS-Net) architecture, which makes use of weight and adjacency modulation, skip connection, and a pure convolutional block with layer normalization. Adjacency modulation facilitates the learning of edges that go beyond the inherent connections of body joints, resulting in an adjusted graph structure that reflects the human skeleton, while skip connections help maintain crucial information from the input layer's initial features as the network depth increases. We evaluate our proposed model on two standard benchmark datasets, and compare it with a comprehensive set of strong baseline methods for 3D human pose estimation. Our experimental results demonstrate that our approach outperforms the baseline methods on both datasets, achieving state-of-the-art performance. Furthermore, we conduct ablation studies to analyze the contributions of different components of our model architecture and show that the skip connection and adjacency modulation help improve the model performance.

cs.CV↗

arXiv2023

Regular Splitting Graph Network for 3D Human Pose Estimation

In human pose estimation methods based on graph convolutional architectures, the human skeleton is usually modeled as an undirected graph whose nodes are body joints and edges are connections between neighboring joints. However, most of these methods tend to focus on learning relationships between body joints of the skeleton using first-order neighbors, ignoring higher-order neighbors and hence limiting their ability to exploit relationships between distant joints. In this paper, we introduce a higher-order regular splitting graph network (RS-Net) for 2D-to-3D human pose estimation using matrix splitting in conjunction with weight and adjacency modulation. The core idea is to capture long-range dependencies between body joints using multi-hop neighborhoods and also to learn different modulation vectors for different body joints as well as a modulation matrix added to the adjacency matrix associated to the skeleton. This learnable modulation matrix helps adjust the graph structure by adding extra graph edges in an effort to learn additional connections between body joints. Instead of using a shared weight matrix for all neighboring body joints, the proposed RS-Net model applies weight unsharing before aggregating the feature vectors associated to the joints in order to capture the different relations between them. Experiments and ablations studies performed on two benchmark datasets demonstrate the effectiveness of our model, achieving superior performance over recent state-of-the-art methods for 3D human pose estimation.

cs.CV↗

arXiv2022

Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On

Previous virtual try-on methods usually focus on aligning a clothing item with a person, limiting their ability to exploit the complex pose, shape and skin color of the person, as well as the overall structure of the clothing, which is vital to photo-realistic virtual try-on. To address this potential weakness, we propose a fill in fabrics (FIFA) model, a self-supervised conditional generative adversarial network based framework comprised of a Fabricator and a unified virtual try-on pipeline with a Segmenter, Warper and Fuser. The Fabricator aims to reconstruct the clothing image when provided with a masked clothing as input, and learns the overall structure of the clothing by filling in fabrics. A virtual try-on pipeline is then trained by transferring the learned representations from the Fabricator to Warper in an effort to warp and refine the target clothing. We also propose to use a multi-scale structural constraint to enforce global context at multiple scales while warping the target clothing to better fit the pose and shape of the person. Extensive experiments demonstrate that our FIFA model achieves state-of-the-art results on the standard VITON dataset for virtual try-on of clothing items, and is shown to be effective at handling complex poses and retaining the texture and embroidery of the clothing.

cs.CV↗

arXiv2022

Masked Supervised Learning for Semantic Segmentation

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to tackle cases where not only the regions of interest are small and ambiguous, but also when there exists an imbalance between the semantic classes. To this end, we propose Masked Supervised Learning (MaskSup), an effective single-stage learning paradigm that models both short- and long-range context, capturing the contextual relationships between pixels via random masking. Experimental results demonstrate the competitive performance of MaskSup against strong baselines in both binary and multi-class segmentation tasks on three standard benchmark datasets, particularly at handling ambiguous regions and retaining better segmentation of minority classes with no added inference cost. In addition to segmenting target regions even when large portions of the input are masked, MaskSup is also generic and can be easily integrated into a variety of semantic segmentation methods. We also show that the proposed method is computationally efficient, yielding an improved performance by 10\% on the mean intersection-over-union (mIoU) while requiring $3\times$ less learnable parameters.

cs.CV↗

arXiv2021

Higher-Order Implicit Fairing Networks for 3D Human Pose Estimation

Estimating a 3D human pose has proven to be a challenging task, primarily because of the complexity of the human body joints, occlusions, and variability in lighting conditions. In this paper, we introduce a higher-order graph convolutional framework with initial residual connections for 2D-to-3D pose estimation. Using multi-hop neighborhoods for node feature aggregation, our model is able to capture the long-range dependencies between body joints. Moreover, our approach leverages residual connections, which are integrated by design in our network architecture, ensuring that the learned feature representations retain important information from the initial features of the input layer as the network depth increases. Experiments and ablations studies conducted on two standard benchmarks demonstrate the effectiveness of our model, achieving superior performance over strong baseline methods for 3D human pose estimation.

cs.CV↗

arXiv2021

STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification

Semi-supervised learning (SSL) has proven to be effective at leveraging large-scale unlabeled data to mitigate the dependency on labeled data in order to learn better models for visual recognition and classification tasks. However, recent SSL methods rely on unlabeled image data at a scale of billions to work well. This becomes infeasible for tasks with relatively fewer unlabeled data in terms of runtime, memory and data acquisition. To address this issue, we propose noisy semi-supervised transfer learning, an efficient SSL approach that integrates transfer learning and self-training with noisy student into a single framework, which is tailored for tasks that can leverage unlabeled image data on a scale of thousands. We evaluate our method on both binary and multi-class classification tasks, where the objective is to identify whether an image displays people practicing sports or the type of sport, as well as to identify the pose from a pool of popular yoga poses. Extensive experiments and ablation studies demonstrate that by leveraging unlabeled data, our proposed framework significantly improves visual classification, especially in multi-class classification settings compared to state-of-the-art methods. Moreover, incorporating transfer learning not only improves classification performance, but also requires 6x less compute time and 5x less memory. We also show that our method boosts robustness of visual classification models, even without specifically optimizing for adversarial robustness.

cs.CV↗

arXiv2021

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low- and high-level convolutional features, resulting in not only blurred feature maps, but also over- and under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.

eess.IV↗

arXiv2021

A Federated Learning Approach to Anomaly Detection in Smart Buildings

Internet of Things (IoT) sensors in smart buildings are becoming increasingly ubiquitous, making buildings more livable, energy efficient, and sustainable. These devices sense the environment and generate multivariate temporal data of paramount importance for detecting anomalies and improving the prediction of energy usage in smart buildings. However, detecting these anomalies in centralized systems is often plagued by a huge delay in response time. To overcome this issue, we formulate the anomaly detection problem in a federated learning setting by leveraging the multi-task learning paradigm, which aims at solving multiple tasks simultaneously while taking advantage of the similarities and differences across tasks. We propose a novel privacy-by-design federated learning model using a stacked long short-time memory (LSTM) model, and we demonstrate that it is more than twice as fast during training convergence compared to the centralized LSTM. The effectiveness of our federated learning approach is demonstrated on three real-world datasets generated by the IoT production system at General Electric Current smart building, achieving state-of-the-art performance compared to baseline methods in both classification and regression tasks. Our experimental results demonstrate the effectiveness of the proposed framework in reducing the overall training cost without compromising the prediction performance.

cs.LG↗

arXiv2021

Synthetic COVID-19 Chest X-ray Dataset for Computer-Aided Diagnosis

We introduce a new dataset called Synthetic COVID-19 Chest X-ray Dataset for training machine learning models. The dataset consists of 21,295 synthetic COVID-19 chest X-ray images to be used for computer-aided diagnosis. These images, generated via an unsupervised domain adaptation approach, are of high quality. We find that the synthetic images not only improve performance of various deep learning architectures when used as additional training data under heavy imbalance conditions, but also detect the target class with high confidence. We also find that comparable performance can also be achieved when trained only on synthetic images. Further, salient features of the synthetic COVID-19 images indicate that the distribution is significantly different from Non-COVID-19 classes, enabling a proper decision boundary. We hope the availability of such high fidelity chest X-ray images of COVID-19 will encourage advances in the development of diagnostic and/or management tools.

eess.IV↗

arXiv2021

Ridge Regression Neural Network for Pediatric Bone Age Assessment

Bone age is an important measure for assessing the skeletal and biological maturity of children. Delayed or increased bone age is a serious concern for pediatricians, and needs to be accurately assessed in a bid to determine whether bone maturity is occurring at a rate consistent with chronological age. In this paper, we introduce a unified deep learning framework for bone age assessment using instance segmentation and ridge regression. The proposed approach consists of two integrated stages. In the first stage, we employ an image annotation and segmentation model to annotate and segment the hand from the radiographic image, followed by background removal. In the second stage, we design a regression neural network architecture composed of a pre-trained convolutional neural network for learning salient features from the segmented pediatric hand radiographs and a ridge regression output layer for predicting the bone age. Experimental evaluation on a dataset of hand radiographs demonstrates the competitive performance of our approach in comparison with existing deep learning based methods for bone age assessment.

cs.CV↗

arXiv2020

WISE: A Computer System Performance Index Scoring Framework

The performance levels of a computing machine running a given workload configuration are crucial for both users and providers of computing resources. Knowing how well a computing machine is running with a given workload configuration is critical to making proper computing resource allocation decisions. In this paper, we introduce a novel framework for deriving computing machine and computing resource performance indicators for a given workload configuration. We propose a workload/machine index score (WISE) framework for computing a fitness score for a workload/machine combination. The WISE score indicates how well a computing machine is running with a specific workload configuration by addressing the issue of whether resources are being stressed or sitting idle wasting precious resources. In addition to encompassing any number of computing resources, the WISE score is determined by considering how far from target levels the machine resources are operating at without maxing out. Experimental results demonstrate the efficacy of the proposed WISE framework on two distinct workload configurations.

cs.DC↗

arXiv2020

Synthesis of COVID-19 Chest X-rays using Unpaired Image-to-Image Translation

Motivated by the lack of publicly available datasets of chest radiographs of positive patients with Coronavirus disease 2019 (COVID-19), we build the first-of-its-kind open dataset of synthetic COVID-19 chest X-ray images of high fidelity using an unsupervised domain adaptation approach by leveraging class conditioning and adversarial training. Our contributions are twofold. First, we show considerable performance improvements on COVID-19 detection using various deep learning architectures when employing synthetic images as additional training set. Second, we show how our image synthesis method can serve as a data anonymization tool by achieving comparable detection performance when trained only on synthetic data. In addition, the proposed data generation framework offers a viable solution to the COVID-19 detection in particular, and to medical image classification tasks in general. Our publicly available benchmark dataset consists of 21,295 synthetic COVID-19 chest X-ray images. The insights gleaned from this dataset can be used for preventive actions in the fight against the COVID-19 pandemic.

eess.IV↗

arXiv2020

Anisotropic Graph Convolutional Network for Semi-supervised Learning

Graph convolutional networks learn effective node embeddings that have proven to be useful in achieving high-accuracy prediction results in semi-supervised learning tasks, such as node classification. However, these networks suffer from the issue of over-smoothing and shrinking effect of the graph due in large part to the fact that they diffuse features across the edges of the graph using a linear Laplacian flow. This limitation is especially problematic for the task of node classification, where the goal is to predict the label associated with a graph node. To address this issue, we propose an anisotropic graph convolutional network for semi-supervised node classification by introducing a nonlinear function that captures informative features from nodes, while preventing oversmoothing. The proposed framework is largely motivated by the good performance of anisotropic diffusion in image and geometry processing, and learns nonlinear representations based on local graph structure and node features. The effectiveness of our approach is demonstrated on three citation networks and two image datasets, achieving better or comparable classification accuracy results compared to the standard baseline methods.

cs.LG↗

arXiv2020

Melanoma Detection using Adversarial Training and Deep Transfer Learning

Skin lesion datasets consist predominantly of normal samples with only a small percentage of abnormal ones, giving rise to the class imbalance problem. Also, skin lesion images are largely similar in overall appearance owing to the low inter-class variability. In this paper, we propose a two-stage framework for automatic classification of skin lesion images using adversarial training and transfer learning toward melanoma detection. In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis by learning the inter-class mapping and synthesizing under-represented class samples from the over-represented ones using unpaired image-to-image translation. In the second stage, we train a deep convolutional neural network for skin lesion classification using the original training set combined with the newly synthesized under-represented class samples. The training of this classifier is carried out by minimizing the focal loss function, which assists the model in learning from hard examples, while down-weighting the easy ones. Experiments conducted on a dermatology image benchmark demonstrate the superiority of our proposed approach over several standard baseline methods, achieving significant performance improvements. Interestingly, we show through feature visualization and analysis that our method leads to context based lesion assessment that can reach an expert dermatologist level.

eess.IV↗

arXiv2017

Global spectral graph wavelet signature for surface analysis of carpal bones

In this paper, we present a spectral graph wavelet approach for shape analysis of carpal bones of human wrist. We apply a metric called global spectral graph wavelet signature for representation of cortical surface of the carpal bone based on eigensystem of Laplace-Beltrami operator. Furthermore, we propose a heuristic and efficient way of aggregating local descriptors of a carpal bone surface to global descriptor. The resultant global descriptor is not only isometric invariant, but also much more efficient and requires less memory storage. We perform experiments on shape of the carpal bones of ten women and ten men from a publicly-available database. Experimental results show the excellency of the proposed GSGW compared to recent proposed GPS embedding approach for comparing shapes of the carpal bones across populations.

cs.GR↗

arXiv2017

Shape Classification using Spectral Graph Wavelets

Spectral shape descriptors have been used extensively in a broad spectrum of geometry processing applications ranging from shape retrieval and segmentation to classification. In this pa- per, we propose a spectral graph wavelet approach for 3D shape classification using the bag-of-features paradigm. In an effort to capture both the local and global geometry of a 3D shape, we present a three-step feature description framework. First, local descriptors are extracted via the spectral graph wavelet transform having the Mexican hat wavelet as a generating ker- nel. Second, mid-level features are obtained by embedding lo- cal descriptors into the visual vocabulary space using the soft- assignment coding step of the bag-of-features model. Third, a global descriptor is constructed by aggregating mid-level fea- tures weighted by a geodesic exponential kernel, resulting in a matrix representation that describes the frequency of appearance of nearby codewords in the vocabulary. Experimental results on two standard 3D shape benchmarks demonstrate the effective- ness of the proposed classification approach in comparison with state-of-the-art methods.

cs.GR↗

arXiv2015

Spectral Graph Theoretic Analysis of Tsallis Entropy-based Dissimilarity Measure

In this paper we introduce a nonextensive quantum information theoretic measure which may be defined between any arbitrary number of density matrices, and we analyze its fundamental properties in the spectral graph-theoretic framework. Unlike other entropic measures, the proposed quantum divergence is symmetric, matrix-convex, theoretically upper-bounded, and has the advantage of being generalizable to any arbitrary number of density matrices, with a possibility of assigning weights to these densities.

cs.IT↗

arXiv2015

A Multicomponent Approach to Nonrigid Registration of Diffusion Tensor Images

We propose a nonrigid registration approach for diffusion tensor images using a multicomponent information-theoretic measure. Explicit orientation optimization is enabled by incorporating tensor reorientation, which is necessary for wrapping diffusion tensor images. Experimental results on diffusion tensor images indicate the feasibility of the proposed approach and a much better performance compared to the affine registration method based on mutual information in terms of registration accuracy in the presence of geometric distortion.

cs.CV↗