Browse > Methodology > AutoML > Neural Architecture Search

Neural Architecture Search

138 papers with code · Methodology
Subtask of AutoML

Leaderboards

Latest papers with code

To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing

11 Feb 2020apourchot/to_share_or_not_to_share

Weight-sharing (WS) has recently emerged as a paradigm to accelerate the automated search for efficient neural architectures, a process dubbed Neural Architecture Search (NAS).

NEURAL ARCHITECTURE SEARCH

1
11 Feb 2020

Variational Depth Search in ResNets

6 Feb 2020anonimoose12345678/arch_uncert

One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost.

NEURAL ARCHITECTURE SEARCH

0
06 Feb 2020

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search

28 Jan 2020automl/nasbench-1shot1

One-shot neural architecture search (NAS) has played a crucial role in making NAS methods computationally feasible in practice.

NEURAL ARCHITECTURE SEARCH

10
28 Jan 2020

MixPath: A Unified Approach for One-shot Neural Architecture Search

16 Jan 2020xiaomi-automl/MixPath

The expressiveness of search space is a key concern in neural architecture search (NAS).

NEURAL ARCHITECTURE SEARCH

1
16 Jan 2020

Neural Architecture Search for Deep Image Prior

14 Jan 2020Pol22/NAS_DIP

We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP).

IMAGE RESTORATION NEURAL ARCHITECTURE SEARCH SUPER-RESOLUTION

1
14 Jan 2020

Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

8 Jan 2020JaminFong/FNA

In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH OBJECT DETECTION SEMANTIC SEGMENTATION

39
08 Jan 2020

NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search

2 Jan 2020D-X-Y/NAS-Projects

A variety of algorithms search architectures under different search space.

DATA AUGMENTATION NEURAL ARCHITECTURE SEARCH

731
02 Jan 2020

FasterSeg: Searching for Faster Real-time Semantic Segmentation

ICLR 2020 TAMU-VITA/FasterSeg

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods.

NEURAL ARCHITECTURE SEARCH REAL-TIME SEMANTIC SEGMENTATION

175
01 Jan 2020

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

ICLR 2020 meijieru/AtomNAS

We propose a fine-grained search space comprised of atomic blocks, a minimal search unit much smaller than the ones used in recent NAS algorithms.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH

107
01 Jan 2020

NAS evaluation is frustratingly hard

ICLR 2020 antoyang/NAS-Benchmark

As such, and due to the under-use of ablation studies, there is a lack of clarity regarding why certain methods are more effective than others.

NEURAL ARCHITECTURE SEARCH

53
01 Jan 2020