April 2025

MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search

arXiv · Apr 22 · Research Healthcare

The paper introduces MedNNS, a neural network search framework designed for medical imaging, addressing challenges in architecture selection and weight initialization. MedNNS constructs a meta-space encoding datasets and models based on their performance using a Supernetwork-based approach, expanding the model zoo size by 51x. The framework incorporates rank loss and Fréchet Inception Distance (FID) loss to capture inter-model and inter-dataset relationships, improving alignment in the meta-space and outperforming ImageNet pre-trained DL models and SOTA NAS methods.

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models

arXiv · Apr 16 · CV Research

This paper introduces SemDiff, a novel method for generating unrestricted adversarial examples (UAEs) by exploring the semantic latent space of diffusion models. SemDiff uses multi-attribute optimization to ensure attack success while preserving the naturalness and imperceptibility of generated UAEs. Experiments on high-resolution datasets demonstrate SemDiff's superior performance compared to state-of-the-art methods in attack success rate and imperceptibility, while also evading defenses.

Leveraging Social Media Analytics for Sustainability Trend Detection in Saudi Arabias Evolving Market

arXiv · Apr 22 · Research NLP

Enhancing Pothole Detection and Characterization: Integrated Segmentation and Depth Estimation in Road Anomaly Systems

arXiv · Apr 18 · CV Research