Text

Towards Efficient U-Nets : A Coupled and Quantized Approach

In this paper, we propose to couple stacked U-Nets for efficient visual landmark localization. The key idea is to globally reuse features of the same semantic meanings across the stacked U-Nets. The feature reuse makes each U-Net light-weighted. Specially, we propose an order-K coupling design to trim off long-distance shortcuts, together with an iterative refinement and memory sharing mechanism. To further improve the efficiency, we quantize the parameters, intermediate features, and gradients of the coupled U-Nets to low bit-width numbers. We validate our approach in two tasks: human pose estimation and facial landmark localization. The results show that our approach achieves state-of-the-art localization accuracy but using ~ 70% fewer parameters, ~ 30% less inference time, ~ 98% less model size, and saving ~ 75% training memory compared with benchmark localizers.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.42 No.8 August 2020

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 2038 - 2050

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

FACE ALIGNMENT
HUMAN POSE ESTIMATION
STACKED U-NETS
DENSE CONNECTIVITY
NETWORK QUANTIZATION
EFFICIENT AI

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Zhiqiang Tang, Xi Peng, Kang Li, Dimitris N. Metaxas

Versi lain/terkait

Lampiran Berkas

Komentar