New ICLR Submissions
stes opened this issue · comments
Just as a quick link list, here is a list of ICLR Submissions using the keyword "Domain Adaptation". I guess waiting for the reviews makes sense before including them in the reading list.
Unsupervised DA
- A Collaborative Low-Rank Reconstructive Layer for Domain Shift Problems
- Confidence Regularized Self-Training
- Variational Domain Adaptation
- Cosine similarity-based Adversarial process
- DOMAIN ADAPTATION VIA DISTRIBUTION AND REPRESENTATION MATCHING: A CASE STUDY ON TRAINING DATA SELECTION VIA REINFORCEMENT LEARNING
- Unsupervised Domain Adaptation for Distance Metric Learning
Open set
- Learning Factorized Representations for Open-Set Domain Adaptation
- Reducing Overconfident Errors outside the Known Distribution
Translation Based
- Augmented Cyclic Adversarial Learning for Domain Adaptation
- Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
Adversarial Adaptation
Dataset based
- Dataset Distillation
- Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
Unsupervised
Applications
Multidomain Learning/Domain Generalization
- Multi-Domain Adversarial Learning
- GradMix: Multi-source Transfer across Domains and Tasks
- The Natural Language Decathlon: Multitask Learning as Question Answering
- Semi-supervised Learning with Multi-Domain Sentiment Word Embeddings
- Meta Domain Adaptation: Meta-Learning for Few-Shot Learning under Domain Shift
- Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach
Adv Examples as Domain Shift
- Improving the Generalization of Adversarial Training with Domain Adaptation
- SPIGAN: Privileged Adversarial Learning from Simulation
Unsorted
Great, thanks for making this list, some of them look very interesting! I guess we can indeed wait a bit for the official publication.
Since the decision of ICLR 2019 was made, I think we can put some of the new papers into the list.😄
@STayinloves Yes, I will go through the list and open a PR over the weekend.