Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions
We develop an algorithm to improve the performance of a pre-trained model under concept shift without retraining the model from scratch when only unannotated samples of initial concepts are accessible. We model this problem as a domain adaptation problem, where the source domain data is inaccessible during model adaptation. The core idea is based on consolidating the intermediate internal distribution, learned to represent the source domain data, after adapting the model. We provide theoretical analysis and conduct extensive experiments to demonstrate that the proposed method is effective.
Code (1)
Tasks
Domain AdaptationTransfer LearningUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Overcoming label shift in targeted federated learning
Federated learning enables multiple actors to collaboratively train models without sharing private data. This unlocks the potential for scaling machine learning to diverse applications. Existing algorithms for this task …
Federated Learningimage-classificationImage ClassificationProxy Methods for Domain Adaptation
We study the problem of domain adaptation under distribution shift, where the shift is due to a change in the distribution of an unobserved, latent variable that confounds both the covariates and the labels. In this sett…
Domain AdaptationMonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly…
3D Object DetectionDepth EstimationDiversityDomain Adaptation+5Concept-aware clustering for decentralized deep learning under temporal shift
Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts. While non-iid data has been extensively studied in distributed settings, temporal shi…
ClusteringDeep LearningMind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
Machine learning models often perform poorly under subpopulation shifts in the data distribution. Developing methods that allow machine learning models to better generalize to such shifts is crucial for safe deployment i…
AttributeBayesian Inference