arXiv subjects

Waleed Abdulla

Publications and source records attributed to Waleed Abdulla.

10 recordsLinked to original sources

arXiv2026

Luce: Relightable Gaussians for 3D Asset Generation

High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. However, preserving fine detail across the physically based rendering (PBR) modalities needed for relighting remains challenging. To address this, we propose Luce, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for albedo, metallic-roughness, and surface normals. A variational autoencoder compresses this representation into a unified material-aware latent space. A rectified-flow transformer generates this latent from a single image using multi-layer features from a pretrained image encoder that preserve both semantic context and fine spatial detail. The latent is then decoded into relightable PBR Gaussians and an optional textured mesh with a tangent-space normal map. On Toys4K, Luce achieves state-of-the-art single-image-to-3D generation, improving FID by 28% over the strongest baseline. We further evaluate Luce on a benchmark of AI-generated images depicting diverse subjects and materials, where it improves the CLIP image-alignment score over the best baseline (0.8519 vs. 0.8299). Luce generates relightable, geometrically accurate, and materially faithful assets that preserve fine details such as text, logos, and inscriptions.

cs.CV↗

arXiv2026

Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning

Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability. While synthetic data can address these gaps, traditional methods often require extensive speaker-specific data, reintroducing the collection bottleneck. We investigate zero-shot voice cloning as a low-burden augmentation strategy, using Higgs Audio V2 to clone speakers in the TORGO dataset. We fine-tune (FT) Whisper-medium on cloned, real, and hybrid data and evaluate on held-out real speech. Compared to the zero-shot (31.62%), Clone FT achieved a competitive 26.00% WER, nearly matching the 24.44% and 25.12% seen with Real and Hybrid FT, respectively. Notably, Clone and Hybrid FT outperform Real FT for moderate-severe speakers. Clone FT achieves the best results (11.45% relative) in cross-corpus evaluation on the SAP-1102. These results suggest that zero-shot cloning provides scalable training data that circumvents the costly data collection bottleneck.

eess.AS↗

arXiv2026

Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition

Backpropagation remains the dominant algorithm for training deep neural networks, but it incurs substantial memory overhead and relies on global error propagation, which is often regarded as biologically implausible. The Forward-Forward (FF) algorithm is an appealing local-learning alternative to backpropagation, yet it still lags behind backpropagation in accuracy. A central unresolved question is whether this gap arises from FF's locality or from the positive-negative double-pass goodness objective used to train each layer. In this work, we revisit FF under the supervised setting through a decomposition that separates these two design choices. Our analysis suggests that FF's performance limitations are not explained by locality alone, but are also likely influenced by its goodness objective. Motivated by this view, we introduce Mono-Forward (MF), a simplification of FF that preserves its locality while replacing the contrastive goodness objective with a standard multi-class cross-entropy objective applied locally at each layer, serving as a controlled baseline for evaluating local learning under a standard classification objective. Across MLPs and convolutional networks, MF outperforms vanilla FF and remains competitive in multiple FF variants. On MLP-Mixers, MF achieves stronger results on PathMNIST than backpropagation while requiring only 31% of backpropagation's memory.

cs.LG↗

arXiv2025

Reshaping the Forward-Forward Algorithm with a Similarity-Based Objective

Backpropagation is the pivotal algorithm underpinning the success of artificial neural networks, yet it has critical limitations such as biologically implausible backward locking and global error propagation. To circumvent these constraints, the Forward-Forward algorithm was proposed as a more biologically plausible method that replaces the backward pass with an additional forward pass. Despite this advantage, the Forward-Forward algorithm significantly trails backpropagation in accuracy, and its optimal form exhibits low inference efficiency due to multiple forward passes required. In this work, the Forward-Forward algorithm is reshaped through its integration with similarity learning frameworks, eliminating the need for multiple forward passes during inference. This proposed algorithm is named Forward-Forward Algorithm Unified with Similarity-based Tuplet loss (FAUST). Empirical evaluations on MNIST, Fashion-MNIST, and CIFAR-10 datasets indicate that FAUST substantially improves accuracy, narrowing the gap with backpropagation. On CIFAR-10, FAUST achieves 56.22\% accuracy with a simple multi-layer perceptron architecture, approaching the backpropagation benchmark of 57.63\% accuracy.

cs.LG↗

arXiv2025

Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation

Honey is an important commodity in the global market. Honey types of different botanical origins provide diversified flavors and health benefits, thus having different market values. Developing accurate and effective botanical origin-distinguishing techniques is crucial to protect consumers' interests. However, it is impractical to collect all the varieties of honey products at once to train a model for botanical origin differentiation. Therefore, researchers developed class-incremental learning (CIL) techniques to address this challenge. This study examined and compared multiple CIL algorithms on a real-world honey hyperspectral imaging dataset. A novel technique is also proposed to improve the performance of class-incremental learning algorithms by combining with a continual backpropagation (CB) algorithm. The CB method addresses the issue of loss-of-plasticity by reinitializing a proportion of less-used hidden neurons to inject variability into neural networks. Experiments showed that CB improved the performance of most CIL methods by 1-7\%.

cs.CV↗

arXiv2025

Transformers Meet Hyperspectral Imaging: A Comprehensive Study of Models, Challenges and Open Problems

Transformers have become the architecture of choice for learning long-range dependencies, yet their adoption in hyperspectral imaging (HSI) is still emerging. We reviewed more than 300 papers published up to 2025 and present the first end-to-end survey dedicated to Transformer-based HSI classification. The study categorizes every stage of a typical pipeline-pre-processing, patch or pixel tokenization, positional encoding, spatial-spectral feature extraction, multi-head self-attention variants, skip connections, and loss design-and contrasts alternative design choices with the unique spatial-spectral properties of HSI. We map the field's progress against persistent obstacles: scarce labeled data, extreme spectral dimensionality, computational overhead, and limited model explainability. Finally, we outline a research agenda prioritizing valuable public data sets, lightweight on-edge models, illumination and sensor shifts robustness, and intrinsically interpretable attention mechanisms. Our goal is to guide researchers in selecting, combining, or extending Transformer components that are truly fit for purpose for next-generation HSI applications.

cs.CV↗

arXiv2025

Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition

In this paper, we present a speaker-independent dysarthric speech recognition system, with a focus on evaluating the recently released Speech Accessibility Project (SAP-1005) dataset, which includes speech data from individuals with Parkinson's disease (PD). Despite the growing body of research in dysarthric speech recognition, many existing systems are speaker-dependent and adaptive, limiting their generalizability across different speakers and etiologies. Our primary objective is to develop a robust speaker-independent model capable of accurately recognizing dysarthric speech, irrespective of the speaker. Additionally, as a secondary objective, we aim to test the cross-etiology performance of our model by evaluating it on the TORGO dataset, which contains speech samples from individuals with cerebral palsy (CP) and amyotrophic lateral sclerosis (ALS). By leveraging the Whisper model, our speaker-independent system achieved a CER of 6.99% and a WER of 10.71% on the SAP-1005 dataset. Further, in cross-etiology settings, we achieved a CER of 25.08% and a WER of 39.56% on the TORGO dataset. These results highlight the potential of our approach to generalize across unseen speakers and different etiologies of dysarthria.

cs.SD↗

arXiv2024

On filter design in deep convolutional neural network

The deep convolutional neural network (DCNN) in computer vision has given promising results. It is widely applied in many areas, from medicine, agriculture, self-driving car, biometric system, and almost all computer vision-based applications. Filters or weights are the critical elements responsible for learning in DCNN. Backpropagation has been the primary learning algorithm for DCNN and provides promising results, but the size and numbers of the filters remain hyper-parameters. Various studies have been done in the last decade on semi-supervised, self-supervised, and unsupervised methods and their properties. The effects of filter initialization, size-shape selection, and the number of filters on learning and optimization have not been investigated in a separate publication to collate all the options. Such attributes are often treated as hyper-parameters and lack mathematical understanding. Computer vision algorithms have many limitations in real-life applications, and understanding the learning process is essential to have some significant improvement. To the best of our knowledge, no separate investigation has been published discussing the filters; this is our primary motivation. This study focuses on arguments for choosing specific physical parameters of filters, initialization, and learning technic over scattered methods. The promising unsupervised approaches have been evaluated. Additionally, the limitations, current challenges, and future scope have been discussed in this paper.

cs.CV↗

arXiv2020

An Efficient Framework for Automated Screening of Clinically Significant Macular Edema

The present study proposes a new approach to automated screening of Clinically Significant Macular Edema (CSME) and addresses two major challenges associated with such screenings, i.e., exudate segmentation and imbalanced datasets. The proposed approach replaces the conventional exudate segmentation based feature extraction by combining a pre-trained deep neural network with meta-heuristic feature selection. A feature space over-sampling technique is being used to overcome the effects of skewed datasets and the screening is accomplished by a k-NN based classifier. The role of each data-processing step (e.g., class balancing, feature selection) and the effects of limiting the region-of-interest to fovea on the classification performance are critically analyzed. Finally, the selection and implication of operating point on Receiver Operating Characteristic curve are discussed. The results of this study convincingly demonstrate that by following these fundamental practices of machine learning, a basic k-NN based classifier could effectively accomplish the CSME screening.

eess.IV↗

arXiv2017

Automatic Segmentation of Retinal Vasculature

Segmentation of retinal vessels from retinal fundus images is the key step in the automatic retinal image analysis. In this paper, we propose a new unsupervised automatic method to segment the retinal vessels from retinal fundus images. Contrast enhancement and illumination correction are carried out through a series of image processing steps followed by adaptive histogram equalization and anisotropic diffusion filtering. This image is then converted to a gray scale using weighted scaling. The vessel edges are enhanced by boosting the detail curvelet coefficients. Optic disk pixels are removed before applying fuzzy C-mean classification to avoid the misclassification. Morphological operations and connected component analysis are applied to obtain the segmented retinal vessels. The performance of the proposed method is evaluated using DRIVE database to be able to compare with other state-of-art supervised and unsupervised methods. The overall segmentation accuracy of the proposed method is 95.18% which outperforms the other algorithms.

cs.CV↗