REVIEW 6 cited by
Unsupervised Domain Adaptation through Self-Supervision
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data. Like much of previous work, we seek to align the learned representations of the source and target domains while preserving discriminability. The way we accomplish alignment is by learning to perform auxiliary self-supervised task(s) on both domains simultaneously. Each self-supervised task brings the two domains closer together along the direction relevant to that task. Training this jointly with the main task classifier on the source domain is shown to successfully generalize to the unlabeled target domain. The presented objective is straightforward to implement and easy to optimize. We achieve state-of-the-art results on four out of seven standard benchmarks, and competitive results on segmentation adaptation. We also demonstrate that our method composes well with another popular pixel-level adaptation method.
Forward citations
Cited by 6 Pith papers
-
MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training
MMEarth-Bench introduces five global multimodal environmental tasks, and TTT-MMR adapts pretrained models at test time by reconstructing 12 auxiliary modalities, improving average performance on both random and geogra...
-
Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
NAVIA augments the [CLS] token with adaptive biases in shallow ViT layers so entropy-minimizing test-time adaptation can recover information lost to token aggregation, reporting over 2.5% accuracy gains and over 20% l...
-
FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment
Aligning the L2-norm statistics of noise predictions during diffusion sampling improves domain adaptation for dense prediction, with a source-free version guided by high-confidence regions.
-
Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluation
Aligning simulated and observed summaries improves neural Bayesian inference under likelihood misspecification but degrades it under prior misspecification.
-
Box Pose and Shape Estimation and Domain Adaptation for Large-Scale Warehouse Automation
BOSS uses certificate-checked pseudo-labels to self-train a stereo keypoint network, improving box pose and shape estimates on real warehouse data without manual labels.
-
SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images
SynthGenNet reports 49.79 mIoU on IDD and 48.33 on Cityscapes by mixing multiple synthetic sources with diverse self-supervised losses, but the method actually uses unlabeled target images during training, so it is no...
Discussion (0). Continue with ORCID to comment.