Text

Fast and Unsupervised Neural Architecture Evolution for Visual Representation Learning

Unsupervised visual representation learning is one of the hottest topics in computer vision, yet performance still lags behind compared with the best supervised learning methods. At the same time, neural architecture search (NAS) has produced state-of-the-art results on various visual tasks. It is a natural idea to explore NAS as a way to improve unsupervised representation learning, yet it remains largely unexplored. In this paper, we propose a Fast and Unsupervised Neural Architecture Evolution (FaUNAE) method to evolve an existing architecture, manually constructed or the result of NAS on a small dataset, to a new architecture that can operate on a larger dataset. This partial optimization can utilize prior knowledge to reduce search cost and improve search efficiency. The evolution is self-supervised where the contrast loss is used as the evaluation metric in a student-teacher framework. By eliminating the inferior or least promising operations, the evolutionary process is greatly accelerated. Experimental results show that we achieve state-of-the-art performance for downstream applications, such as object recognition, object detection, and instance segmentation.

Ketersediaan

Informasi Detail

Judul Seri

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE; Vol.16 No.3 August 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 22 - 32

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

COMPUTER ARCHITECTURE
COMPUTER VISION
NEURAL NETWORKS
MEASUREMENT
VISUALIZATION
BENTUK GALAKSI
UNSUPERVISED LEARNING
SUPERVISED LEARNING
OBJECT DETECTION

Info Detail Spesifik

DOI: 10.1109/MCI.2021.3084394

Pernyataan Tanggungjawab

Song Xue, Hanlin Chen, Chunyu Xie, Baochang Zhang, Xuan Gong, David Doermann

Versi lain/terkait

Lampiran Berkas

Komentar