LtC-MSDA

Domain Adaptation Framework

An implementation of a knowledge aggregation method for adapting to multiple domains using a graph-based framework.

Implementation of Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation (ECCV 2020).

GitHub

69 stars
6 watching
16 forks
Language: Python
last commit: over 2 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
lhoyer/hrda A framework for unsupervised domain adaptation in semantic segmentation using multi-resolution training and learned scale attention. 236
domainadaptation/salad A toolbox for comparing and running domain adaptation algorithms on different datasets. 334
bupt-ai-cz/meta-selflearning Develops a method to improve performance of computer vision tasks by adapting models to new domains and data sources through meta-learning and self-learning techniques. 199
easezyc/deep-transfer-learning A collection of implementations of algorithms to adapt deep learning models from one domain to another 898
wasidennis/adaptsegnet This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another. 851
naoto0804/cross-domain-detection Develops object detection algorithms to adapt to new domains with limited supervision 422
wenkehuang/rethinkfl Improves federated learning performance by incorporating domain knowledge and regularization to adapt models across diverse domains 93
lhoyer/mic An unsupervised domain adaptation method that uses contextual information to improve performance on visual recognition tasks 271
arunmallya/piggyback Adapting a single network to multiple tasks by learning to mask weights 183
liyxi/adaptnas An approach to improve neural architecture search by adapting architectures between domains to improve generalization performance on new datasets. 7
canqin001/pointdan Develops a deep learning model for domain adaptation on 3D point cloud data 130
mediabrain-sjtu/feddg-ga This project presents a method for federated domain generalization with adjustment, allowing multiple models to learn from each other across different domains. 43
billdthompson/cogsci-auto-norm Automatically generates concreteness estimates for languages using pre-trained semantic models and linear regression 0
davisyoshida/lorax A JAX transform that simplifies the training of large language models by reducing memory usage through low-rank adaptation. 134
cal-adapt/climakitae A Python toolkit for accessing and analyzing climate data from the Cal-Adapt Analytics Engine. 21