Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
Revisiting batch normalization for practical domain adaptation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain. Recent study (Tommasi et al. 2015) shows that a DNN has strong dependency towards the training dataset, and the learned features cannot be easily transferred to a different but relevant task without fine-tuning. In this paper, we propose a simple yet powerful remedy, called Adaptive Batch Normalization (AdaBN) to increase the generalization ability of a DNN. By modulating the statistics in all Batch Normalization layers across the network, our approach achieves deep adaptation effect for domain adaptation tasks. In contrary to other deep learning domain adaptation methods, our method does not require additional components, and is parameter-free. It archives state-of-the-art performance despite its surprising simplicity. Furthermore, we demonstrate that our method is complementary with other existing methods. Combining AdaBN with existing domain adaptation treatments may further improve model performance.
verdicts
UNVERDICTED 7representative citing papers
A test-time adaptation framework anchors adversarial training to a non-robust teacher's predictions, yielding more stable optimization and better robustness-accuracy trade-offs than standard self-consistency methods.
APCoTTA introduces a continual test-time adaptation method for ALS point cloud semantic segmentation using gradient-driven layer selection, entropy-based consistency loss, and random parameter interpolation, with new benchmarks showing mIoU gains of 9-14%.
EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.
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.
DoSReMC improves cross-domain generalization in mammography classification by fine-tuning only batch normalization and fully connected layers of pretrained CNNs while preserving convolutional filters, combined with adversarial training.
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.
citing papers explorer
-
Environment Probing Interaction Policies
EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.