Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders
Sergio Lanza, Jae Hee Lee, Stefan Wermter
Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioning and Visual Question Answe…
cs.CV2026
Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions
Thomas Vitry, Kieran Edgeworth, Stefan Wermter +1
Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches to bias mitigation and analy…
cs.CV2024
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
Jae Hee Lee, Georgii Mikriukov, Gesina Schwalbe +2
Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising field of research, since explanations that refer to concepts (i.e., semantically meaningful…