paper-with-me

홈 › Papers

BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels

2020-03-22 · Zan Shen, Jiang Qian, Bojin Zhuang, Shaojun Wang, Jing Xiao

One-Shot methods have evolved into one of the most popular methods in Neural Architecture Search (NAS) due to weight sharing and single training of a supernet. However, existing methods generally suffer from two issues: predetermined number of channels in each layer which is suboptimal; and model averaging effects and poor ranking correlation caused by weight coupling and continuously expanding search space. To explicitly address these issues, in this paper, a Broadening-and-Shrinking One-Shot NAS (BS-NAS) framework is proposed, in which broadening' refers to broadening the search space with a spring block enabling search for numbers of channels during training of the supernet; while shrinking' refers to a novel shrinking strategy gradually turning off those underperforming operations. The above innovations broaden the search space for wider representation and then shrink it by gradually removing underperforming operations, followed by an evolutionary algorithm to efficiently search for the optimal architecture. Extensive experiments on ImageNet illustrate the effectiveness of the proposed BS-NAS as well as the state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2003.09821

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

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

AutoPruning for Deep Neural Network with Dynamic Channel Masking

2020-10-22 · Baopu Li, Yanwen Fan, Zhihong Pan, Gang Zhang

Modern deep neural network models are large and computationally intensive. One typical solution to this issue is model pruning. However, most current pruning algorithms depend on hand crafted rules or domain expertise. T…

AutoMLNetwork Pruning

ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit

2023-04-10 · Brian Yan, Jiatong Shi, Yun Tang, Hirofumi Inaguma 외

ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community. ESPnet-ST-v2 supports 1) offline speech-to-text translation (ST), 2) si…

BenchmarkingSimultaneous Speech-to-Text TranslationSpeech-to-Speech TranslationSpeech-to-Text+2

On- Device Information Extraction from Screenshots in form of tags

2020-01-11 · Sumit Kumar, Gopi Ramena, Manoj Goyal, Debi Mohanty 외

We propose a method to make mobile screenshots easily searchable. In this paper, we present the workflow in which we: 1) preprocessed a collection of screenshots, 2) identified script presentin image, 3) extracted unstru…

FormTAG

Partial Channel Dependence with Channel Masks for Time Series Foundation Models

2024-10-30 · Seunghan Lee, Taeyoung Park, Kibok Lee

Recent advancements in foundation models have been successfully extended to the time series (TS) domain, facilitated by the emergence of large-scale TS datasets. However, previous efforts have primarily focused on design…

Anomaly DetectionImputationTime Series

Deep Learning Enabled Real-Time Photoacoustic Tomography System via Single Data Acquisition Channel

2020-01-21 · Hengrong Lan, Daohuai Jiang, Feng Gao, Fei Gao

Photoacoustic computed tomography (PACT) combines the optical contrast of optical imaging and the penetrability of sonography. In this work, we develop a novel PACT system to provide real-time imaging, which is achieved …