A representation learning approach for multi-source domain adaptation achieves identifiability by partitioning the label's Markov blanket into parents, children, and spouses.
hub
Deep domain con- fusion: Maximizing for domain invariance
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.
hub tools
verdicts
UNVERDICTED 12representative citing papers
Two tunable domain adaptation methods using unrolled networks achieve improved or comparable performance to domain-specific models on compressed sensing regression tasks.
VaRDASS improves unsupervised domain adaptation by using stratified sampling to reduce variance in discrepancy estimation for measures like correlation alignment and MMD, with derived error bounds, an optimality proof for MMD under assumptions, and a k-means style algorithm.
EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.
A domain-adaptive hashing method with intersectant GANs for cross-domain image reconstruction outperforms prior methods on object recognition and retrieval across four benchmarks.
ADaCoRe enables memory-bounded UICL for EEG by compressing and reconstructing signals while preserving key morphologies, outperforming baselines with gains of at least +2.7 and +15.3 ACC on ISRUC and FACED datasets.
Three frameworks adapt foundation models for generalized category discovery under domain shifts via disentanglement and prompt tuning, showing gains on synthetic and real multi-domain data.
PAS estimates target accuracy for domain adaptation by measuring compatibility between source domains, pre-trained feature extractors, and target tasks using embeddings, correlating strongly with actual post-adaptation performance.
Lightweight input adapters preprocess images to match ideal-condition training data for off-the-shelf CV models, enabling self-supervised incremental adaptation and reported gains in segmentation and localization on RobotCar and BDD datasets.
EKTM introduces router, transmitter, and enhanced modules to transfer knowledge across multi-task CVR models, outperforming prior methods with a 3.93% eCPM uplift in online A/B tests on a commercial platform.
A domain-adversarial LSTM learns invariant features from labeled source RUL data to enable predictions in unlabeled target domains with distribution shifts due to varying conditions and fault modes.
An RKHS-MMD domain adaptation method yields better chest X-ray classification across medical centers than non-adapted models by aligning source and target feature distributions.
citing papers explorer
-
A General Representation-Based Approach to Multi-Source Domain Adaptation
A representation learning approach for multi-source domain adaptation achieves identifiability by partitioning the label's Markov blanket into parents, children, and spouses.
-
Tunable Domain Adaptation Using Unfolding
Two tunable domain adaptation methods using unrolled networks achieve improved or comparable performance to domain-specific models on compressed sensing regression tasks.
-
Variance Matters: Improving Domain Adaptation via Stratified Sampling
VaRDASS improves unsupervised domain adaptation by using stratified sampling to reduce variance in discrepancy estimation for measures like correlation alignment and MMD, with derived error bounds, an optimality proof for MMD under assumptions, and a k-means style algorithm.
-
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.
-
One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
A domain-adaptive hashing method with intersectant GANs for cross-domain image reconstruction outperforms prior methods on object recognition and retrieval across four benchmarks.
-
Adaptive Data Compression and Reconstruction for Memory-Bounded EEG Continual Learning
ADaCoRe enables memory-bounded UICL for EEG by compressing and reconstructing signals while preserving key morphologies, outperforming baselines with gains of at least +2.7 and +15.3 ACC on ISRUC and FACED datasets.
-
Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
Three frameworks adapt foundation models for generalized category discovery under domain shifts via disentanglement and prompt tuning, showing gains on synthetic and real multi-domain data.
-
PAS: Estimating the target accuracy before domain adaptation
PAS estimates target accuracy for domain adaptation by measuring compatibility between source domains, pre-trained feature extractors, and target tasks using embeddings, correlating strongly with actual post-adaptation performance.
-
Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
Lightweight input adapters preprocess images to match ideal-condition training data for off-the-shelf CV models, enabling self-supervised incremental adaptation and reported gains in segmentation and localization on RobotCar and BDD datasets.
-
Effective Knowledge Transfer for Multi-Task Recommendation Models
EKTM introduces router, transmitter, and enhanced modules to transfer knowledge across multi-task CVR models, outperforming prior methods with a 3.93% eCPM uplift in online A/B tests on a commercial platform.
-
Remaining Useful Lifetime Prediction via Deep Domain Adaptation
A domain-adversarial LSTM learns invariant features from labeled source RUL data to enable predictions in unlabeled target domains with distribution shifts due to varying conditions and fault modes.
-
A Robust Unsupervised Domain Adaptation Framework for Medical Image Classification Using RKHS-MMD
An RKHS-MMD domain adaptation method yields better chest X-ray classification across medical centers than non-adapted models by aligning source and target feature distributions.