Adversarial Learning for Semi-Supervised Semantic Segmentation

Abstract

We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial resolution. We show that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model. In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory signals. In contrast to existing methods that utilize weakly-labeled images, our method leverages unlabeled images to enhance the segmentation model. Experimental results on the PASCAL VOC 2012 and Cityscapes datasets demonstrate the effectiveness of the proposed algorithm.

Accepted in BMVC 2018. Code and models available at https://github.com/hfslyc/AdvSemiSeg

References in corpus (6)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Fully Convolutional Multi-Class Multiple Instance Learning
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Generative Face Completion

Cited by in corpus (43)

• Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images
• Semi-supervised semantic segmentation needs strong, varied perturbations
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images
• Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study
• Self-paced and self-consistent co-training for semi-supervised image segmentation
• Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
• Video Semantic Segmentation with Distortion-Aware Feature Correction
• Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
• A Comprehensive Review of Modern Object Segmentation Approaches
• Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
• Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training
• CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
• A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos
• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
• SemiCurv: Semi-Supervised Curvilinear Structure Segmentation
• On Regularized Losses for Weakly-supervised CNN Segmentation
• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
• Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
• Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
• Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images
• Uncertainty Inspired RGB-D Saliency Detection
• Revisiting consistency for semi-supervised semantic segmentation
• Mask-based Data Augmentation for Semi-supervised Semantic Segmentation
• Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation
• Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary
• Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
• Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
• Few-Shot Semantic Segmentation Augmented with Image-Level Weak Annotations
• Semi-supervised Domain Adaptation for Semantic Segmentation
• Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images
• Discovering Latent Classes for Semi-Supervised Semantic Segmentation
• A Macro-Micro Weakly-supervised Framework for AS-OCT Tissue Segmentation
• Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation
• Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing
• Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
• Quantifying Topology In Pancreatic Tubular Networks From Live Imaging 3D Microscopy
• Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
• Learning with Weak Annotations for Robust Maritime Obstacle Detection