Research map / Architectures and efficiency / Neural architecture search
Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
Yunyang Xiong, Ronak Mehta, Vikas Singh
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 |
|---|---|---|---|
| add block diversity (search over all six block types instead of only type 5) (ablation) | RCNet · CIFAR-100 | top-1 accuracy: 75.8 -> 76.1 | Improved |
| use the greedy search procedure instead of random blocks for the last several blocks (ablation) | RCNet · CIFAR-100 | top-1 accuracy: 74.9 -> 76.1 | Improved |
| randomly add one more block to the searched architecture (ablation) | RCNet · CIFAR-100 | top-1 accuracy: 76.1 -> 75.1 | Hurt |
| add accumulated random blocks (diminishing returns of accuracy with early stopping) | RCAS set function · CIFAR-100 | top-1 accuracy: 56.96% -> 60.72% over eight additions, gains shrinking | Improved |
| RCNet instead of MobileNetV2 on CIFAR-100 | RCNet · CIFAR-100 | top-1 accuracy: 74.2 -> 76.1 | Improved |
| RCNet instead of DARTS on CIFAR-100 | RCNet · CIFAR-100 | top-1 accuracy: 75.9 -> 76.1 | Improved |
| RCNet instead of MobileNetV2 on ImageNet | RCNet · ImageNet val | top-1 accuracy: 72.0 -> 72.2 | Improved |
| RCNet-B instead of DARTS on ImageNet | RCNet-B · ImageNet val | top-1 accuracy: 73.1 -> 74.7 | Improved |
| RCNet-B versus MNasNet-92 on ImageNet | RCNet-B · ImageNet val | top-1 accuracy: 74.8 -> 74.7 | No clear effect |
| transfer the CIFAR-100 searched architecture to ImageNet | RCNet · ImageNet val | top-1 accuracy | No clear effect |
| RCNet instead of MobileNetV2 on iPhone 5s | RCNet · iPhone 5s CoreML | inference time (ms): 197.2 -> 183.5 | No clear effect |
Closest papers by meaning
- UNAS: Differentiable Architecture Search Meets Reinforcement Learning (CVPR 2020 · similarity 0.88)
- AOWS: Adaptive and Optimal Network Width Search With Latency Constraints (CVPR 2020 · similarity 0.87)
- MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation (CVPR 2020 · similarity 0.87)
- ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation (CVPR 2019 · similarity 0.87)
- XNAS: Neural Architecture Search with Expert Advice (NeurIPS 2019 · similarity 0.87)
- Subnet-Aware Dynamic Supernet Training for Neural Architecture Search (CVPR 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.
