activity
20242026
collaborators

15 papers

cs.CV2026

RECOUNT: Reference-guided Counting with Synthetic Visual Exemplars

Adriano D'Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh

Text-guided zero-shot object counters excel at spatial localization but categorize poorly on novel or fine-grained classes: natural language is too coarse to fully specify visual i…

math.SP2026

Spectral Effects Of Heavy-Tailed Vertex Noise In Geometric Graphs

Ben Cardoen, Jeremy Budd, Enrico Amico +2

We characterize which local matrix structures saturate Weyl's eigenvalue perturbation bound for graph Laplacians under geometrically constrained vertex displacements. Geometric gra…

cs.CV2025

FiGO: Fine-Grained Object Counting without Annotations

Adriano D'Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh

Class-agnostic counting (CAC) methods reduce annotation costs by letting users define what to count at test-time through text or visual exemplars. However, current open-vocabulary…

cs.CY2025

Making Power Explicable in AI: Analyzing, Understanding, and Redirecting Power to Operationalize Ethics in AI Technical Practice

Weina Jin, Elise Li Zheng, Ghassan Hamarneh

The operationalization of ethics in the technical practices of artificial intelligence (AI) is facing significant challenges. To address the problem of ineffective implementation o…

cs.CV2025

What Can We Learn from Inter-Annotator Variability in Skin Lesion Segmentation?

Kumar Abhishek, Jeremy Kawahara, Ghassan Hamarneh

Medical image segmentation exhibits intra- and inter-annotator variability due to ambiguous object boundaries, annotator preferences, expertise, and tools, among other factors. Les…

cs.CY2025

Ethical Medical Image Synthesis

Weina Jin, Ashish Sinha, Kumar Abhishek +1

The task of ethical Medical Image Synthesis (MISyn) is to ensure that the MISyn techniques are researched and developed ethically throughout their entire lifecycle, which is essent…