3 papers
cs.CV2026
DevPrompt: Deviation-Based Prompt Learning for One-Normal ShotImage Anomaly Detection
Morteza Poudineh, Marc Lalonde
Few-normal shot anomaly detection (FNSAD) aims to detect abnormal regions in images using only a few normal training samples, making the task highly challenging due to limited supe…
cs.CV2025
Effectiveness of Large Multimodal Models in Detecting Disinformation: Experimental Results
Yasmina Kheddache, Marc Lalonde
The proliferation of disinformation, particularly in multimodal contexts combining text and images, presents a significant challenge across digital platforms. This study investigat…
cs.CV2025
VLM Models and Automated Grading of Atopic Dermatitis
Marc Lalonde, Hamed Ghodrati
The task of grading atopic dermatitis (or AD, a form of eczema) from patient images is difficult even for trained dermatologists. Research on automating this task has progressed in…