Research map / Architectures and efficiency / CNN design
Convolutional Dynamic Alignment Networks for Interpretable Classifications
Moritz Bohle, Mario Fritz, Bernt Schiele
Check 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 a higher output temperature T (ablation) | CoDA-Net · CIFAR-10 attribution localization | localization metric | Improved |
| Train with T=10.0 rather than T=1000 (ablation) | S-CoDA-SQ · CIFAR-10 | accuracy: 93.2% → 93.6% | Improved |
| Use the SQ nonlinearity rather than L2 normalization (ablation) | CoDA-Net · CIFAR-10 | accuracy: 92.6% → 93.8% | Improved |
| Use the SQ nonlinearity rather than L2 normalization (ablation) | S-CoDA · CIFAR-10 | accuracy: 93.0% → 93.2% | Improved |
| Apply data augmentation (ablation) | CoDA-Net · CIFAR-10 | accuracy | Improved |
| Apply data augmentation (ablation) | XL-CoDA-SQ · TinyImagenet | accuracy: 54.4% → 58.4% | Improved |
| Increase output temperature (ablation) | CoDA-Net · CIFAR-10 | accuracy: 93.2% → 93.6% | Mixed |
| Add L1 regularization on the global linear mapping (ablation) | CoDA-Net · CIFAR-10 attribution maps | heatmap sharpness | Improved |
Closest papers by meaning
- Optimising for Interpretability: Convolutional Dynamic Alignment Networks (TPAMI 2022 · similarity 0.98)
- CLKN: Cascaded Lucas-Kanade Networks for Image Alignment (CVPR 2017 · similarity 0.85)
- Residual Alignment: Uncovering the Mechanisms of Residual Networks (NeurIPS 2023 · similarity 0.85)
- Dynamic Context Correspondence Network for Semantic Alignment (ICCV 2019 · similarity 0.84)
- Dynamic Convolution: Attention Over Convolution Kernels (CVPR 2020 · similarity 0.84)
- Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks (NeurIPS 2025 · similarity 0.83)
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.
