5 papers
When is Test-Time Adaptation Identifiable From Unlabeled Evidence?
Kartik Jhawar, Lipo Wang
Test-time adaptation (TTA) offers many ways to update a deployed model without labels, but choosing the wrong update can make a strong source model worse. Recent methods therefore…
AURA: Active-Response Attribution under Treatment Ambiguity in Bacterial Cytological Profiling
Kartik Jhawar, Mrunmayee Deshpande, Wilfried Moreira +2
When a bacterial sample is exposed to several antibiotics, not every applied drug necessarily acts: if the organism is resistant to one of them, that drug leaves no morphological t…
CHASE: Competing Hypotheses for Ambiguity-Aware Selective Prediction
Kartik Jhawar, Yuhao Geng, Atul N. Parikh +1
Standard selective prediction methods typically estimate uncertainty from the output of a single predictive branch. While effective for general uncertainty estimation, these approa…
Physics-consistent deep learning for blind aberration recovery in mobile optics
Kartik Jhawar, Tamo Sancho Miguel Tandoc, Khoo Jun Xuan +1
Mobile photography is often limited by complex, lens-specific optical aberrations. While recent deep learning methods approach this as an end-to-end deblurring task, these "black-b…
HD-TTA: Hypothesis-Driven Test-Time Adaptation for Safer Brain Tumor Segmentation
Kartik Jhawar, Lipo Wang
Standard Test-Time Adaptation (TTA) methods typically treat inference as a blind optimization task, applying generic objectives to all or filtered test samples. In safety-critical…