Research map / Label-efficient and robust learning / Domain adaptation and generalization
Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add source-label discriminative feature learning with center-based loss to domain alignment | CORAL-based adaptation with Modified LeNet · Digital recognition (Avg) | accuracy: 91.0 -> 94.3 | Helped |
| Add source-label discriminative feature learning with instance-based loss to domain alignment | CORAL-based adaptation with Modified LeNet · Digital recognition (Avg) | accuracy: 91.0 -> 93.8 | Helped |
| Add source-label discriminative feature learning with center-based loss to domain alignment | ResNet domain adaptation · Office-31 (Avg) | accuracy: 78.5 -> 80.2 | Helped |
| Add source-label discriminative feature learning with instance-based loss to domain alignment | ResNet domain adaptation · Office-31 (Avg) | accuracy: 78.5 -> 79.2 | Helped |
| Add the proposed discriminative loss to source classification and domain alignment (ablation) | JDDA on SVHN→MNIST and MNIST→MNIST-M · SVHN→MNIST; MNIST→MNIST-M | test error | Helped |
| Use center-based rather than instance-based discriminative learning (ablation) | JDDA on SVHN→MNIST and MNIST→MNIST-M · SVHN→MNIST; MNIST→MNIST-M | convergence speed | Helped |
| Vary the discriminative-loss weight λ₂ (ablation) | JDDA-I and JDDA-C on SVHN→MNIST · SVHN→MNIST | accuracy | Mixed |
Closest papers by meaning
- Exploiting Local Feature Patterns for Unsupervised Domain Adaptation (AAAI 2019 · similarity 0.91)
- Structure-Aware Feature Fusion for Unsupervised Domain Adaptation (AAAI 2020 · similarity 0.90)
- Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss (CVPR 2019 · similarity 0.90)
- Unsupervised Domain Adaptation With Similarity Learning (CVPR 2018 · similarity 0.90)
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.