Research map / Architectures and efficiency / Neural architecture search
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, Peter Vajda, Joseph E. Gonzalez
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 DMaskingNAS to search compact architectures | ImageNet mobile CNNs · ImageNet (ILSVRC 2012) | Top-1 accuracy: 0.9% higher accuracy | Improved |
| Use DMaskingNAS to search compact architectures | ImageNet mobile CNNs · ImageNet (ILSVRC 2012) | FLOPs: 15% fewer FLOPs | Improved |
| Use DMaskingNAS to search a model under a similar accuracy target | ImageNet mobile CNNs · ImageNet (ILSVRC 2012) | FLOPs: 20% fewer FLOPs | Improved |
| Search FBNetV2 at a similar model size | ImageNet models versus MobileNetV3 · ImageNet (ILSVRC 2012) | Top-1 accuracy: 2.6% | Improved |
| Expand differentiable search to channel and input-resolution dimensions using masking and feature-map reuse | DMaskingNAS · ImageNet architecture search | Search space size: 10^{14}× | Improved |
Closest papers by meaning
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search (CVPR 2019 · similarity 0.88)
- Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search (CVPR 2021 · similarity 0.88)
- NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization (CVPR 2021 · similarity 0.88)
- FP-NAS: Fast Probabilistic Neural Architecture Search (CVPR 2021 · similarity 0.87)
- BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule (CVPR 2022 · similarity 0.87)
- FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining (CVPR 2021 · similarity 0.87)
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.
