TL;DR
A test-time adaptation framework that requires no target-domain supervision that introduces two key innovations: a learnable dynamic augmentation module for better capturing target-domain characteristics, and a self-supervised adaptation strategy for leveraging unlabeled target-domain images by enforcing structural priors and cross-augmentation consistency, thereby improving prediction consistency under domain shift.
Experimental results show that the proposed SFDA object detection framework for the YOLO family of single-stage detectors consistently outperforms the baseline on multiple cross-domain detection tasks, demonstrating its effectiveness and good generalization ability under the source-free setting.
This work designs an adversarial teacher-student framework enhanced with an Auxiliary Masked Autoencoder to learn domain-invariant representations by randomly masking feature regions and enforcing cross-domain reconstruction and introduces an Iterative Consistency Pseudolabel Filter that leverages a memory of historica...
This paper proposes PSP-FSOD, a principled framework that integrates prompt-driven domain simulation with feature perturbation regularization to improve generalization in CD-FSOD, and designs a prompt-driven strategy that leverages the visual grounding capability of large VLMs to jointly model foreground and background...
The proposed Test-time Adaptation via Dual Distillation (TADD), an online adaptation framework that relies on a lightweight projection adapter to bridge the domain gap, conducts extensive evaluations on three well-known video action recognition benchmarks and demonstrates that the method consistently outperforms state-...
Efficient Unsupervised Domain Adaptation (EUDA) is proposed, a parameter-efficient framework that leverages a frozen DINOv2 backbone as a feature extractor and updates only a lightweight bottleneck and classification head to promote both discriminative learning and cross-domain alignment.
A self-supervised contrastive and predictive learning framework that learns discriminative representations directly from unlabeled cross-view image pairs is proposed, which jointly exploits patch-level and pixel-level objectives to capture both fine-grained local changes and higher-level semantic consistency across vie...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
