43 datasets found

Regularized evolution for image classifier architecture search

NATS-Bench: Benchmarking NAS algorithms for architecture topology and size

FreeREA: Training-Free Evolution-based Architecture Search

MAPLE-Edge: A Runtime Latency Predictor for Edge Devices

Stabilizing Differentiable Architecture Search via Perturbation-based Regularization

Noisy Differentiable Architecture Search

Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring...

The dataset used in this paper is a production-scale on-device natural language understanding model.

A benchmark for neural architecture search.

The NASBench-101 dataset is a large-scale benchmark for neural architecture search. It contains nearly 423K unique convolutional neural network architectures with diverse...

ArchExplorer is a visual analysis method for understanding a neural architecture space and summarizing design principles.

The dataset used in the paper is NAS-Bench-301 and AlphaNet. NAS-Bench-301 is a surrogate NAS benchmark built via deep ensembles and modeling uncertainty, which provides...

The dataset used in the paper for Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning

The dataset used in the paper for Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning

The dataset used in the paper for Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning

The dataset used in the paper for Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning

The proposed Siamese-Predictor using EFM to fuse prior knowledge - Estimation Code. The proposed Estimation Code and accuracy of architectures are highly correlated based on our...

The proposed Siamese-Predictor using EFM to fuse prior knowledge - Estimation Code. The proposed Estimation Code and accuracy of architectures are highly correlated based on our...

The proposed Siamese-Predictor using EFM to fuse prior knowledge - Estimation Code. The proposed Estimation Code and accuracy of architectures are highly correlated based on our...

The proposed Siamese-Predictor using EFM to fuse prior knowledge - Estimation Code. The proposed Estimation Code and accuracy of architectures are highly correlated based on our...