MnasNet: Platform-Aware Neural Architecture Search for Mobile
read the original abstract
Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all dimensions, it is very difficult to manually balance these trade-offs when there are so many architectural possibilities to consider. In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike previous work, where latency is considered via another, often inaccurate proxy (e.g., FLOPS), our approach directly measures real-world inference latency by executing the model on mobile phones. To further strike the right balance between flexibility and search space size, we propose a novel factorized hierarchical search space that encourages layer diversity throughout the network. Experimental results show that our approach consistently outperforms state-of-the-art mobile CNN models across multiple vision tasks. On the ImageNet classification task, our MnasNet achieves 75.2% top-1 accuracy with 78ms latency on a Pixel phone, which is 1.8x faster than MobileNetV2 [29] with 0.5% higher accuracy and 2.3x faster than NASNet [36] with 1.2% higher accuracy. Our MnasNet also achieves better mAP quality than MobileNets for COCO object detection. Code is at https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
NCoTS treats chain-of-thought reasoning as a search problem and uses a dual-factor heuristic to find paths that are over 3.5% more accurate and 22% shorter on benchmarks.
-
Neural Input Search for Large Scale Recommendation Models
NIS applies RL to jointly optimize per-feature vocabulary sizes and per-value embedding dimensions under memory constraint, reporting 6.8% Recall@1 and 1.8% ROC-AUC gains over manual baselines on retrieval and ranking tasks.
-
A Unified Optimization Approach for CNN Model Inference on Integrated GPUs
A unified IR plus ML-based scheduling for CNN inference on multi-vendor integrated GPUs matches or exceeds vendor libraries (up to 1.62x) on image models while supporting more models.
-
EPNAS: Efficient Progressive Neural Architecture Search
EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNe...
-
SwiftNet: Using Graph Propagation as Meta-knowledge to Search Highly Representative Neural Architectures
GRAM meta-graph search plus structure pruning yields SwiftNet models with 2.15x higher accuracy density than MobileNet-V2 and 26x lower search cost than FBNet on ImageNet edge constraints.
-
A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
Empirical comparison of transfer learning performance across eleven pre-trained models on five image datasets using accuracy, time, and size metrics.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.