PI-TTA stabilizes source-free test-time adaptation for sensor-based human activity recognition by adding physics-consistent constraints, yielding up to 9.13% accuracy gains and lower physical violation rates on three benchmarks under streaming shifts.
Temporal test-time adaptation with state-space models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
TRUST is a test-time adaptation method for SSM vision models that uses uncertainty-guided traversal permutations to refine Mamba parameters via pseudo-labels and weight averaging, improving robustness on distribution shifts.
TARA uses temporal 3D point clouds and visit-level pseudo-labeling to achieve 100% identification accuracy for group-housed sows without RFID tags.
citing papers explorer
-
PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices
PI-TTA stabilizes source-free test-time adaptation for sensor-based human activity recognition by adding physics-consistent constraints, yielding up to 9.13% accuracy gains and lower physical violation rates on three benchmarks under streaming shifts.
-
TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
TRUST is a test-time adaptation method for SSM vision models that uses uncertainty-guided traversal permutations to refine Mamba parameters via pseudo-labels and weight averaging, improving robustness on distribution shifts.
-
A Non-Invasive Alternative to RFID: Self-Sufficient 3D Identification of Group-Housed Livestock
TARA uses temporal 3D point clouds and visit-level pseudo-labeling to achieve 100% identification accuracy for group-housed sows without RFID tags.