Discriminator-guided adaptive diffusion enables source-free test-time adaptation to 15 image corruption types by dynamically denoising inputs to align with the source domain while preserving discriminative features.
hub
Towards stable test-time adaptation in dynamic wild world
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
IMSE adapts Vision Transformers for test-time and continual test-time adaptation by tuning only singular values from SVD decompositions and using expert diversity plus domain retrieval, reaching SOTA with far fewer trainable parameters.
Low-rank decoder adaptation enables efficient test-time optimization for zero-shot depth completion by updating only the subspace containing depth-relevant information.
Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
CoDiRe blends VLM and target model predictions via MSP-based weighting and Optimal Transport rectification to enable stable continual test-time adaptation, outperforming CoTTA by 10.55% on ImageNet-C at 48% of the compute cost.
CreTTA reformulates test-time adaptation of marginal distributions as residual energy learning, producing a contrastive objective that cancels the partition function and uses relative energy differences for adaptive gradient reweighting to avoid overfitting.
Proposes meta-learning attack with priority-aware gradient alignment for sample-wise targeted attacks on TTA that maintain label distribution consistency with no-attack baseline.
Diversity-aware memory policies improve test-time adaptation performance most under constrained memory budgets and challenging non-i.i.d. streams.
MG-MTTA improves VLM accuracy under modality-specific shifts by replacing pure entropy minimization with majorization-guided adaptation that incorporates a reliability-aware gate prior.
UATTA adapts pre-trained text-image models at test time without labels by using disagreement in bidirectional retrieval rankings to estimate and mitigate uncertainty for improved person search.
SkySeg is a heterogeneous multi-UAV framework that fuses low- and high-definition images and uses cross-device test-time adaptation to enable real-time onboard semantic segmentation, reporting 3.6x faster inference and accuracy gains of 5.91% onboard and 10.91% in the wild.
DynamicGate MLP enables concurrent learning and inference by separating gating from representation parameters, so that even asynchronous updates produce outputs equivalent to a valid fixed model snapshot.