Research map / Architectures and efficiency / CNN design
MintNet: Building Invertible Neural Networks with Masked Convolutions
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 |
|---|---|---|---|
| Use MintNet instead of ResNet | Image classification · MNIST test | accuracy: 99.6% -> 99.6% | No clear effect |
| Use MintNet instead of ResNet | Image classification · CIFAR-10 test | accuracy: 92.6% -> 91.2% | Hurt |
| Use MintNet instead of FFJORD | Generative modeling · MNIST | bits per dimension: 0.99 -> 0.98 | Helped |
| Use MintNet instead of Glow | Generative modeling · CIFAR-10 | bits per dimension: 3.35 -> 3.32 | Helped |
| Use MintNet instead of Glow | Generative modeling · ImageNet 32×32 | bits per dimension: 4.09 -> 4.06 | Helped |
| Use fixed-point inversion rather than triangular forward/back substitutions | MintNet sampling · CIFAR-10 | inversion iterations: 120 iterations; 3072 iterations | Helped |
Closest papers by meaning
- Invertible Residual Networks (ICML 2019 · similarity 0.90)
- i-RevNet: Deep Invertible Networks (ICLR 2018 · similarity 0.89)
- Invertibility of Convolutional Generative Networks from Partial Measurements (NeurIPS 2018 · similarity 0.89)
- Invert to Learn to Invert (NeurIPS 2019 · similarity 0.87)
- Network Inversion of Convolutional Neural Nets (Student Abstract) (AAAI 2025 · similarity 0.85)
- Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks (ICML 2024 · 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.