Research map / Detection and segmentation / CNN features
Learning Strict Identity Mappings in Deep Residual 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 |
|---|---|---|---|
| Add a sparsity-promoting function that sets small residual responses to zero, enabling redundant blocks to be discarded | ResNet · CIFAR-10, CIFAR-100, SVHN | validation error | No clear effect |
| Add a sparsity-promoting function that enables redundant blocks to be discarded | ResNet · ImageNet | validation error | Hurt |
| Increase the ε threshold (ablation) | ε-ResNet · CIFAR-10, CIFAR-100, ImageNet | compression ratio | Helped |
| Add side supervision at the middle of the network (ablation) | ε-ResNet · CIFAR-10, CIFAR-100, SVHN | validation error | Mixed |
Closest papers by meaning
- Are ResNets Provably Better than Linear Predictors? (NeurIPS 2018 · similarity 0.90)
- Residual Alignment: Uncovering the Mechanisms of Residual Networks (NeurIPS 2023 · similarity 0.90)
- Towards Understanding the Importance of Shortcut Connections in Residual Networks (NeurIPS 2019 · similarity 0.89)
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers (NeurIPS 2025 · similarity 0.88)
- LAuReL: Learned Augmented Residual Layer (ICML 2025 · similarity 0.87)
- Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning (CVPR 2024 · 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.