Text

Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency

The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification with limited data has only drawn attention recently. In this work, we propose an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images. The proposed approach relies on adversarial training with a feature matching loss to learn from unlabeled images. It uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The dual-branch approach reduces both the low-level and the high-level artifacts typical when training with few labels. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks-PASCAL VOC 2012, PASCAL-Context, and Cityscapes-the approach achieves new state-of-the-art in semi-supervised learning.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.43 No.4 April 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 1369 - 1379

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

COMPUTER VISION
SEMI-SUPERVISED LEARNING
SEMANTIC SEGMENTATION
GENERATIVE ADVERSARIAL NETWORKS

Info Detail Spesifik

DOI: 10.1109/TPAMI.2019.2960224

Pernyataan Tanggungjawab

Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox

Versi lain/terkait

Lampiran Berkas

Komentar