AI RESEARCH
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
arXiv CS.LG
•
ArXi:2604.22477v1 Announce Type: cross Neuron labeling assigns textual descriptions to internal units of deep networks. Existing approaches typically rely on highly activating examples, often yielding broad or misleading labels by focusing on dominant but incidental visual factors. Prior work such as