Guided Collaborative Training for Pixel-Wise Semi-Supervised Learning

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

138 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2020
Subtitle of host publication16th European Conference, 2020, Proceedings
EditorsAndrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm
PublisherSpringer Nature
Pages429-445
VolumeXIII
ISBN (electronic)978-3-030-58601-0
ISBN (print)978-3-030-58600-3
Publication statusPublished - Aug 2020

Publication series

NameLecture Notes in Computer Science (including subseries Image Processing, Computer Vision, Pattern Recognition, and Graphics)
Volume12358
ISSN (Print)0302-9743
ISSN (electronic)1611-3349

Conference

Title16th European Conference on Computer Vision (ECCV 2020)
LocationOnline
PlaceUnited Kingdom
CityGlasgow
Period23 - 28 August 2020

Abstract

We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs. In addition, existing pixel-wise SSL approaches are only suitable for certain tasks as they usually require to use task-specific properties. In this paper, we present a new SSL framework, named Guided Collaborative Training (GCT), for pixel-wise tasks, with two main technical contributions. First, GCT addresses the issues caused by the dense outputs through a novel flaw detector. Second, the modules in GCT learn from unlabeled data collaboratively through two newly proposed constraints that are independent of task-specific properties. As a result, GCT can be applied to a wide range of pixel-wise tasks without structural adaptation. Our extensive experiments on four challenging vision tasks, including semantic segmentation, real image denoising, portrait image matting, and night image enhancement, show that GCT outperforms state-of-the-art SSL methods by a large margin.

Research Area(s)

  • Pixel-wise vision tasks, Semi-supervised learning

Citation Format(s)

Guided Collaborative Training for Pixel-Wise Semi-Supervised Learning. / Ke, Zhanghan; Qiu, Di; Li, Kaican et al.
Computer Vision – ECCV 2020: 16th European Conference, 2020, Proceedings. ed. / Andrea Vedaldi; Horst Bischof; Thomas Brox; Jan-Michael Frahm. Vol. XIII Springer Nature, 2020. p. 429-445 (Lecture Notes in Computer Science (including subseries Image Processing, Computer Vision, Pattern Recognition, and Graphics); Vol. 12358).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review