Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Diagnosing and Mitigating Evidence Misgrounding in Multimodal Knowledge Editing
Zhiwu Wang, Yichen Wu, Jinqian Yang +4
Multimodal knowledge editing aims to update visually grounded facts in Multimodal Large Language Models (MLLMs) while preserving unrelated text and visual behaviors. However, stand…
cs.CV2021
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers
Renzhen Wang, De cai, Kaiwen Xiao +3
Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of orde…