{"url":"/method/mnasnet","slug":"mnasnet","name":"MnasNet","full_name":"MnasNet","full_name_withheld":false,"description_markdown":"**MnasNet** is a type of convolutional neural network optimized for mobile devices that is discovered through mobile [neural architecture search](https://paperswithcode.com/method/neural-architecture-search), which explicitly incorporates model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. The main building block is an [inverted residual block](https://paperswithcode.com/method/inverted-residual-block) (from [MobileNetV2](https://paperswithcode.com/method/mobilenetv2)).","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1807.11626v3","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/osmr/imgclsmob/blob/c03fa67de3c9e454e9b6d35fe9cbb6b15c28fda7/pytorch/pytorchcv/models/mnasnet.py#L161","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutional Neural Networks","url":"/methods/category/convolutional-neural-networks","pwc_aliases":[]}],"n_papers_tagged":20,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/the-hidden-dance-of-phonemes-and-visage","title":"The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features","date":"2023-07-26","arxiv_id":"2307.13953","n_code_links":1,"syntology":null},{"paper":"/paper/sar-atr-under-limited-training-data-via","title":"SAR ATR under Limited Training Data Via MobileNetV3","date":"2023-06-27","arxiv_id":"2306.15287","n_code_links":1,"syntology":null},{"paper":null,"title":"Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance","date":"2022-11-26","arxiv_id":"2211.14487","n_code_links":0,"syntology":null},{"paper":"/paper/an-embarrassingly-simple-comparison-of","title":"An embarrassingly simple comparison of machine learning algorithms for indoor scene classification","date":"2021-09-25","arxiv_id":"2109.12261","n_code_links":1,"syntology":null},{"paper":null,"title":"HAO: Hardware-aware neural Architecture Optimization for Efficient Inference","date":"2021-04-26","arxiv_id":"2104.12766","n_code_links":0,"syntology":null},{"paper":null,"title":"Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation","date":"2021-04-19","arxiv_id":"2104.09648","n_code_links":0,"syntology":null},{"paper":null,"title":"Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces","date":"2020-12-16","arxiv_id":"2012.08859","n_code_links":0,"syntology":null},{"paper":"/paper/deep-transfer-learning-for-automated","title":"Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs","date":"2020-11-06","arxiv_id":"2011.04475","n_code_links":1,"syntology":null},{"paper":null,"title":"R-MnasNet: Reduced MnasNet for Computer Vision","date":"2020-10-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/efficientnet-elite-extremely-lightweight-and","title":"EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search","date":"2020-09-16","arxiv_id":"2009.07409","n_code_links":3,"syntology":null},{"paper":null,"title":"Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers","date":"2020-08-12","arxiv_id":"2008.05124","n_code_links":0,"syntology":null},{"paper":"/paper/to-filter-prune-or-to-layer-prune-that-is-the","title":"To Filter Prune, or to Layer Prune, That Is The Question","date":"2020-07-11","arxiv_id":"2007.05667","n_code_links":1,"syntology":null},{"paper":"/paper/fine-grained-stochastic-architecture-search","title":"Fine-Grained Stochastic Architecture Search","date":"2020-06-17","arxiv_id":"2006.09581","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":0}},{"paper":null,"title":"Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices","date":"2020-05-07","arxiv_id":"2005.05085","n_code_links":0,"syntology":null},{"paper":null,"title":"Neural Epitome Search for Architecture-Agnostic Network Compression","date":"2019-07-12","arxiv_id":"1907.05642","n_code_links":0,"syntology":null},{"paper":"/paper/190409925","title":"Attention Augmented Convolutional Networks","date":"2019-04-22","arxiv_id":"1904.09925","n_code_links":14,"syntology":{"ran":3,"of":6,"unverified":3,"pointer_only":1}},{"paper":"/paper/soft-conditional-computation","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","date":"2019-04-10","arxiv_id":"1904.04971","n_code_links":9,"syntology":null},{"paper":"/paper/network-slimming-by-slimmable-networks","title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers","date":"2019-03-27","arxiv_id":"1903.11728","n_code_links":10,"syntology":null},{"paper":"/paper/chamnet-towards-efficient-network-design","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","date":"2018-12-21","arxiv_id":"1812.08934","n_code_links":1,"syntology":null},{"paper":"/paper/mnasnet-platform-aware-neural-architecture","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","date":"2018-07-31","arxiv_id":"1807.11626","n_code_links":29,"syntology":{"ran":2,"of":6,"unverified":4,"pointer_only":2}}],"papers_shown":20,"tasks":[{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":7},{"task":"/task/image-classification","name":"Image Classification","papers":5},{"task":"/task/object-detection","name":"Object Detection","papers":5},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":null,"name":"GPU","papers":2},{"task":"/task/classification","name":"General Classification","papers":2},{"task":"/task/model-compression","name":"Model Compression","papers":2},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/bayesian-optimization","name":"Bayesian Optimization","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/brain-tumor-segmentation","name":"Brain Tumor Segmentation","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/efficient-neural-network","name":"Efficient Neural Network","papers":1},{"task":"/task/hardware-aware-neural-architecture-search","name":"Hardware Aware Neural Architecture Search","papers":1}],"tasks_shown":20,"n_tasks":28,"usage_by_year":[{"year":"2018","papers":2},{"year":"2019","papers":4},{"year":"2020","papers":8},{"year":"2021","papers":3},{"year":"2022","papers":1},{"year":"2023","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mnasnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}