paper-with-me

홈 › Papers

FOX-NAS: Fast, On-device and Explainable Neural Architecture Search

2021-08-14 · Chia-Hsiang Liu, Yu-Shin Han, Yuan-Yao Sung, Yi Lee, Hung-Yueh Chiang, Kai-Chiang Wu

Neural architecture search can discover neural networks with good performance, and One-Shot approaches are prevalent. One-Shot approaches typically require a supernet with weight sharing and predictors that predict the performance of architecture. However, the previous methods take much time to generate performance predictors thus are inefficient. To this end, we propose FOX-NAS that consists of fast and explainable predictors based on simulated annealing and multivariate regression. Our method is quantization-friendly and can be efficiently deployed to the edge. The experiments on different hardware show that FOX-NAS models outperform some other popular neural network architectures. For example, FOX-NAS matches MobileNetV2 and EfficientNet-Lite0 accuracy with 240% and 40% less latency on the edge CPU. FOX-NAS is the 3rd place winner of the 2020 Low-Power Computer Vision Challenge (LPCVC), DSP classification track. See all evaluation results at https://lpcv.ai/competitions/2020. Search code and pre-trained models are released at https://github.com/great8nctu/FOX-NAS.

📄 PDF Abstract BibTeX arXiv:2108.08189

Code (1)

great8nctu/fox-nas 공식 구현

Tasks

CPUNeural Architecture SearchQuantization

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Inverted Residual Block 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification

2021-01-10 · Yao Qiang, Supriya Tumkur Suresh Kumar, Marco Brocanelli, Dongxiao Zhu

On-device Deep Neural Networks (DNNs) have recently gained more attention due to the increasing computing power of the mobile devices and the number of applications in Computer Vision (CV), Natural Language Processing (N…

Adversarial RobustnessGeneral ClassificationKnowledge DistillationModel Compression+2

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

2021-02-08 · Renqian Luo, Xu Tan, Rui Wang, Tao Qin 외

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small mem…

CPUModel CompressionNeural Architecture Searchtext-to-speech+1

Explainable AI using expressive Boolean formulas

2023-06-06 · Gili Rosenberg, J. Kyle Brubaker, Martin J. A. Schuetz, Grant Salton 외

We propose and implement an interpretable machine learning classification model for Explainable AI (XAI) based on expressive Boolean formulas. Potential applications include credit scoring and diagnosis of medical condit…

BenchmarkingExplainable Artificial Intelligence (XAI)Interpretable Machine Learning

Model Recovery at the Edge under Resource Constraints for Physical AI

2025-12-01 · Bin Xu, Ayan Banerjee, Sandeep K. S. Gupta arxiv

Model Recovery (MR) enables safe, explainable decision making in mission-critical autonomous systems (MCAS) by learning governing dynamical equations, but its deployment on edge devices is hindered by the iterative natur…

Decision Making

AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement

2022-03-29 · Mayukh Das, Brijraj Singh, Harsh Kanti Chheda, Pawan Sharma 외

Designing suitable deep model architectures, for AI-driven on-device apps and features, at par with rapidly evolving mobile hardware and increasingly complex target scenarios is a difficult task. Though Neural Architectu…

AutoMLNeural Architecture Search