Research map / Architectures and efficiency / CNN design
i-RevNet: Deep Invertible Networks
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 an injective i-RevNet instead of a ResNet | Image classification · ILSVRC-2012 | top-1 error: 24.7 -> 24.7 | No clear effect |
| Use a bijective i-RevNet instead of a RevNet | Image classification · ILSVRC-2012 | top-1 error: 25.2 -> 26.7 | Hurt |
| Preserve information through invertible layers while learning the representation | i-RevNet · ImageNet, 100-class validation subset | Top-1 accuracy | Helped |
| Project the final representation onto its first principal components, retaining d > 200 | i-RevNet features · ImageNet, 100-class task | classification accuracy | No clear effect |
Closest papers by meaning
- Invertibility of Convolutional Generative Networks from Partial Measurements (NeurIPS 2018 · similarity 0.91)
- Invertible Residual Networks (ICML 2019 · similarity 0.90)
- MintNet: Building Invertible Neural Networks with Masked Convolutions (NeurIPS 2019 · similarity 0.89)
- The Reversible Residual Network: Backpropagation Without Storing Activations (NeurIPS 2017 · similarity 0.89)
- Network Inversion of Convolutional Neural Nets (Student Abstract) (AAAI 2025 · similarity 0.87)
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers (NeurIPS 2025 · similarity 0.86)
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.