AI RESEARCH
Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
arXiv CS.AI
•
ArXi:2605.10142v1 Announce Type: cross Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of post-hoc explanations. We investigate this relationship by evaluating 11 computer vision models representing increasing levels of depth and complexity within the ResNet, DenseNet, and Vision Transformer families, trained from scratch or pretrained, across three image datasets with ground-truth segmentation masks.