Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

Abstract

We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding pixels. The in-painted images are then presented to a discriminator network that judges if they are real (unaltered training images) or not. This task acts as a regularizer for standard supervised training of the discriminator. Using our approach we are able to directly train large VGG-style networks in a semi-supervised fashion. We evaluate on STL-10 and PASCAL datasets, where our approach obtains performance comparable or superior to existing methods.

Cited by in corpus (16)

• A Survey on Deep Semi-supervised Learning
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• How Generative Adversarial Networks and Their Variants Work: An Overview
• Stabilizing GAN Training with Multiple Random Projections
• Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
• Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective
• Attribute Restoration Framework for Anomaly Detection
• IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
• Self-Supervised Feature Learning by Learning to Spot Artifacts
• Attribute-Guided Sketch Generation
• Channel-Recurrent Autoencoding for Image Modeling
• Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
• Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
• Fine-grained Action Segmentation using the Semi-Supervised Action GAN