- Parameter Transfer Unit for Deep Neural Networks
- Learning Fair and Transferable Representations
- Open Compound Domain Adaptation
- Multi-source Distilling Domain Adaptation
- Discriminative Adversarial Domain Adaptation
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
- CO-Optimal Transport
- Universal Domain Adaptation through Self-Supervision
- Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
- LEEP: A New Measure to Evaluate Transferability of Learned Representations
- A Unified View of Label Shift Estimation
- A survey on domain adaptation theory: learning bounds and theoretical guarantees
- Extending and Analyzing Self-Supervised Learning Across Domains
- Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
- Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
- Graph Optimal Transport for Cross-Domain Alignment
- Transfer Learning via l1 Regularization
- Visualizing Transfer Learning
- Transferable Calibration with Lower Bias and Variance in Domain Adaptation
- Do Adversarially Robust ImageNet Models Transfer Better?
- Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
- An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch
- What is being transferred in transfer learning?
- Overcoming Negative Transfer: A Survey
- Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
- On Adaptive Distance Estimation
- A Combinatorial Perspective on Transfer Learning
- Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
- A Comprehensive Survey on Transfer Learning
- Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
- Learning What and Where to Transfer
- Do Better ImageNet Models Transfer Better?
- Towards Inheritable Models for Open-Set Domain Adaptation
- Model Adaptation: Unsupervised Domain Adaptation without Source Data
- Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
- Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning
- On the Value of Target Data in Transfer Learning
- Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
- Adapting Neural Architectures Between Domains
- Hierarchical Granularity Transfer Learning
- Learning to Adapt to Evolving Domains
- Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
- Transferable Curriculum forWeakly-Supervised Domain Adaptation
- On Learning Invariant Representations for Domain Adaptation
- Learning Classifiers for Target Domain with Limited or No Labels
- Characterizing and Avoiding Negative Transfer
5l1v3r1 / transfer-learning-papers Goto Github PK
View Code? Open in Web Editor NEWThis project forked from manjunath5496/transfer-learning-papers
"They hold up a mirror to the part of ourselves we're trying our best to conceal: that utterly defenseless, deeply tender inner part that yearns for connection and kindness- and can be so easily crushed."― Jennifer Latson