Research map / Architectures and efficiency / RNNs and normalization
Architecture Disentanglement for Deep Neural Networks
Jie Hu, Liujuan Cao, Tong Tong, Qixiang Ye, Shengchuan Zhang, Ke Li, Feiyue Huang, Ling Shao, Rongrong Ji
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 |
|---|---|---|---|
| compare misclassified-label sub-architectures with other labels | VGG16 · ImageNet | average sub-architecture similarity (%): 78.59 vs 73.74 (Dif. -4.85) | Improved |
| compare misclassified-label sub-architectures with other labels | DARTS-Net · ImageNet | average sub-architecture similarity (%): 60.02 vs 52.97 (Dif. -7.05) | Improved |
| compare misclassified-label sub-architectures with other labels | ResNet50 · Place365 | average sub-architecture similarity (%): 65.49 vs 60.34 (Dif. -5.15) | Improved |
| compare misclassified-label sub-architectures with other labels | DenseNet121 · ImageNet | average sub-architecture similarity (%): 53.35 vs 51.41 (Dif. -1.94) | Improved |
Closest papers by meaning
- Demystifying Inductive Biases for (Beta-)VAE Based Architectures (ICML 2021 · similarity 0.86)
- Network Dissection: Quantifying Interpretability of Deep Visual Representations (CVPR 2017 · similarity 0.86)
- Refining Architectures of Deep Convolutional Neural Networks (CVPR 2016 · similarity 0.86)
- Layerwise Change of Knowledge in Neural Networks (ICML 2024 · similarity 0.86)
- Disentangling Representations through Multi-task Learning (ICLR 2025 · similarity 0.85)
- Training the Untrainable: Introducing Inductive Bias via Representational Alignment (NeurIPS 2025 · similarity 0.84)
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.
