2 citations · 2 across the 2 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models
Muhammad Atif Butt, Paweł Skierś, Joost Van De Weijer +1
Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear directions in activation space…
cs.CV2020★ 2 cited
Self-Training for Class-Incremental Semantic Segmentation
Lu Yu, Xialei Liu, Joost van de Weijer
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer…