6 papers · 1 filter
Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
Tim Nielen, Sameer Ambekar, Johannes Kiechle +2
Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distributi…
Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation
Sameer Ambekar, Marta Hasny, Laura Daza +2
Test-time adaptation allows pretrained models to adjust to incoming data streams, addressing distribution shifts between source and target domains. However, standard methods rely o…
The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging
Sameer Ambekar, Reza Nasirigerdeh, Peter J. Schuffler +3
Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, w…
GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts
Sameer Ambekar, Zehao Xiao, Xiantong Zhen +1
We consider the problem of test-time domain generalization, where a model is trained on several source domains and adjusted on target domains never seen during training. Different…
Selective Test-Time Adaptation for Unsupervised Anomaly Detection using Neural Implicit Representations
Sameer Ambekar, Julia A. Schnabel, Cosmin I. Bercea
Deep learning models in medical imaging often encounter challenges when adapting to new clinical settings unseen during training. Test-time adaptation offers a promising approach t…
Probabilistic Test-Time Generalization by Variational Neighbor-Labeling
Sameer Ambekar, Zehao Xiao, Jiayi Shen +2
This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation…