paper-with-me

홈 › Papers

Fine-Grained Neural Architecture Search

2019-11-18 · Heewon Kim, Seokil Hong, Bohyung Han, Heesoo Myeong, Kyoung Mu Lee

We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature maps using several different base operations. FGNAS runs efficiently in spite of significantly large search space compared to other methods because it trains networks end-to-end by a stochastic gradient descent method. Moreover, the proposed framework allows to optimize the network under predefined resource constraints in terms of number of parameters, FLOPs and latency. FGNAS has been applied to two crucial applications in resource demanding computer vision tasks---large-scale image classification and image super-resolution---and demonstrates the state-of-the-art performance through flexible operation search and channel pruning.

📄 PDF Abstract BibTeX arXiv:1911.07478

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationImage Super-ResolutionNeural Architecture SearchSuper-Resolution

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Fine-Grained Stochastic Architecture Search

2020-06-17 · Shraman Ray Chaudhuri, Elad Eban, Hanhan Li, Max Moroz 외

State-of-the-art deep networks are often too large to deploy on mobile devices and embedded systems. Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods ar…

Neural Architecture Searchobject-detectionObject Detection

ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity

2021-03-17 · ICCV 2021 10 · Dan Ruta, Saeid Motiian, Baldo Faieta, Zhe Lin 외

We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style. Representation learning is critical to visual search, where distance in the learned search e…

AllRepresentation Learning

Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search

2021-12-09 · Yifan Jiang, Xinyu Gong, Junru Wu, Humphrey Shi 외

Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often computationally intensive and not suitable…

Neural Architecture SearchVideo RecognitionVideo Understanding

AtomNAS: Fine-Grained End-to-End Neural Architecture Search

2019-12-20 · ICLR 2020 1 · Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin 외

Search space design is very critical to neural architecture search (NAS) algorithms. We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in rec…

Neural Architecture Search

Impostor Networks for Fast Fine-Grained Recognition

2018-06-13 · Vadim Lebedev, Artem Babenko, Victor Lempitsky

In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-gra…

GPU