Research map / Label-efficient and robust learning / Recognition and long-tail
Task-Driven Common Representation Learning via Bridge Neural Network
Yao Xu, Xueshuang Xiang, Meiyu Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use task-specific positive pairs based on matching digit labels rather than a shared positive-pair construction | BNN · MNIST cross-view transfer learning | accuracy: 77.05 -> 90.21; 78.81 -> 91.38 | Improved |
| Use randomly sampled negative pairs instead of all possible negative pairs (ablation) | BNN · Small sub-dataset | performance | No clear effect |
| Use lightweight convolutional layers instead of fully connected layers (ablation) | BNN · MNIST | pair matching and CCA performance | No clear effect |
Closest papers by meaning
- BA-Net: Bridge Attention for Deep Convolutional Neural Networks (ECCV 2022 · similarity 0.85)
- Gradients as Features for Deep Representation Learning (ICLR 2020 · similarity 0.84)
- Cross-Stitch Networks for Multi-Task Learning (CVPR 2016 · similarity 0.84)
- Similarity and Matching of Neural Network Representations (NeurIPS 2021 · similarity 0.83)
- Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation (NeurIPS 2018 · similarity 0.83)
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks (ICML 2024 · similarity 0.82)
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.
