Search Results for author:
Found 7 papers, 3 papers with code
Diversity-aware Buffer for Coping with Temporally Correlated Data Streams in Online Test-time Adaptation
In real-world scenarios, test data streams are not always independent and identically distributed (i. i. d.).
Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction
To tackle the problem of universal TTA, we identify and highlight several challenges a self-training based method has to deal with: 1) model bias and the occurrence of trivial solutions when performing entropy minimization on varying sequence lengths with and without multiple domain shifts, 2) loss of generalization which exacerbates the adaptation to multiple domain shifts and the occurrence of catastrophic forgetting, and 3) performance degradation due to shifts in class prior.
Robust Mean Teacher for Continual and Gradual Test-Time Adaptation
We demonstrate the effectiveness of our proposed method 'robust mean teacher' (RMT) on the continual and gradual corruption benchmarks CIFAR10C, CIFAR100C, and Imagenet-C. We further consider ImageNet-R and propose a new continual DomainNet-126 benchmark.
Introducing Intermediate Domains for Effective Self-Training during Test-Time
In this work, we address two problems that exist when applying self-training in the setting of test-time adaptation.
Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer
In this work, we focus on UDA and additionally address the case of adapting not only to a single domain, but to a sequence of target domains.
An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions
Integrating different representations from complementary sensing modalities is crucial for robust scene interpretation in autonomous driving.
Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
To avoid the costly annotation of training data for unseen domains, unsupervised domain adaptation (UDA) attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain.
Ranked #20 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
