Mohamed Fahmy Tolba

Change detection (CD) in remote sensing imagery is essential for monitoring urban growth, land-use transformation, and environmental dynamics. However, cross-domain change detection remains challenging due to distribution shifts caused by differences in geographic regions, spatial resolutions, sensor/acquisition conditions, temporal periods, and annotation protocols. This paper introduces CrossCD-Eval, a unified framework for evaluating the generalization of deep learning-based change detection models under in-domain, cross-domain, and few-shot domain adaptation settings. Five recent models, namely GLAFormer ¹ , Change-Mamba ² , EHCTNet ³ , ELGC-Net ⁴ , and STNet ⁵ , are evaluated using CLCD, HRSCD, and LEVIR-CD. To reduce representation-level domain mismatch, we propose a Domain-Aware Feature Normalization (DAFN) module that aligns source and target feature statistics as a lightweight feature-level adaptation component. Experimental results show that all models achieve strong in-domain performance but degrade under cross-domain transfer, confirming the impact of domain shift. DAFN improves cross-domain and few-shot adaptation performance, with larger gains observed under more challenging source–target shifts. Repeated 10-shot experiments over five random target-sample selections further show that DAFN improves adaptation stability, reducing IoU standard deviation by up to 22.7%. An additional ablation and baseline-comparison study demonstrates that the observed gains are not solely due to preprocessing. Compared with full preprocessing, AdaBN, adversarial feature alignment, and the instance-normalization-based CrossCDNet baseline, DAFN provides additional feature-level adaptation benefits, especially when combined with strong backbones such as STNet.

Background: Early cancer diagnosis is essential for improving prognosis and guiding treatment. However, the high dimensionality and complexity of omics data present major challenges. Computational approaches that extract stable biomarkers and enable reliable classification across cancer types and stages are needed. Methods: A novel feature selection method, sDCFE (synergistic Discriminative Cluster-based Feature Extraction), was developed by extending Fisher-like variance analysis with a median absolute deviation (MAD) regularization term and a cluster separation component to enhance robustness and interpretability. Features selected by sDCFE were compared with those obtained from XGBoost, and the intersected set of 82 genes was evaluated through functional enrichment (KEGG, Reactome, GO BP), survival analysis (Kaplan–Meier, Cox regression), and biomarker novelty assessment against six external resources. Hybrid classification models integrating XGBoost, sDCFE, and deep learning were applied to pancancer classification, and the framework was further extended to lung squamous cell carcinoma (LUSC) staging using RNA-seq and methylation data. Results: The overlap between sDCFE and XGBoost yielded 82 candidate biomarkers enriched in cancer-related pathways, including cell cycle regulation, immune signalling, and DNA repair. Novelty assessment stratified these genes into established, emerging, and novel categories. Six genes—HFE2, LOC339674, SERINC2, SFTA3, SOX2OT, and ACPP—emerged as the most promising candidates, supported by enrichment and survival associations across multiple cancers. The hybrid model achieved near-perfect pancancer classification on TCGA (accuracy = 99.3%, MCC = 0.992, AUC = 1.0) and demonstrated strong generalizability on PCAWG (accuracy = 94%, MCC = 0.929, AUC = 0.997). In the LUSC staging task, multiomics integration improved classification performance: the CNN-based model reached 84% accuracy, while logistic regression applied to sDCFE-ranked features achieved 88.5% accuracy with superior calibration, highlighting the robustness of the selected features. Conclusion: sDCFE provides a principled extension of Fisher-like methods, enabling stable and interpretable biomarker selection. When combined with XGBoost and deep learning, the framework achieves highly accurate and biologically grounded cancer classification across both cancer types and stages. The identification of novel and prognostic biomarkers, including HFE2, LOC339674, SERINC2, SFTA3, SOX2OT, and ACPP, underscores its translational potential. These results position the framework as a promising precision oncology tool to support early diagnosis, risk stratification, and treatment decision-making.

The Scene Graph is a modern structured representation of an image scene that explicitly describes the scene as a set of objects, attributes, and links between the objects (relationships). With the great advancements in the computer vision field, researchers dedicated their efforts towards more complex reasoning and a high level of understanding of visual scenes. Tasks like Visual Question Answering, image generation, and cross-modal retrieval are examples of Complex vision tasks that require a high level of visual scene understanding. Scene Graph is an effective data structure that highlights complex visual relationships presented in a scene. In this work, we provide a comparative analysis of Scene Graph Generation (SGG) backbone models. The contributed work aims to compare the Convolution Neural Networks (CNN) backbones and the vision transformer-based backbones using the RelTR model. The conducted analysis proved that both SwiftFormer L3 and MiT-B2 transformer backbones increased the model performance over the ResNet50 CNN backbone by 2.1 % and 2.5% Recall@50 respectively when experimented on the same Visual Genome 50 test split. The Visual Genome 50 is a tailored version of The Visual Genome dataset. It contains only the 50 most common relationships and the most frequent 150 object classes.