Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
arXiv:1810.04377 · doi:10.1007/s11704-018-7195-8
Abstract
Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the field of computer vision. The recent application of deep representation learning has driven this field into a new stage of development. In this paper, we summarize three aspects of the progress of research on semantic image parsing, i.e., category-level semantic segmentation, instance-level semantic segmentation, and beyond segmentation. Specifically, we first review the general frameworks for each task and introduce the relevant variants. The advantages and limitations of each method are also discussed. Moreover, we present a comprehensive comparison of different benchmark datasets and evaluation metrics. Finally, we explore the future trends and challenges of semantic image parsing.
References in corpus (39)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Sequence to Sequence Learning with Neural Networks
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Fully Convolutional Networks for Semantic Segmentation
- A Critical Review of Recurrent Neural Networks for Sequence Learning
- Pixel Recurrent Neural Networks
- Multi-Scale Context Aggregation by Dilated Convolutions
- ParseNet: Looking Wider to See Better
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Learning Deconvolution Network for Semantic Segmentation
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Deep Human Parsing with Active Template Regression
- Pyramid Scene Parsing Network
- Grid Long Short-Term Memory
- Fully Connected Deep Structured Networks
- Semantic Instance Segmentation via Deep Metric Learning
- Simultaneous Detection and Segmentation
- Semantic Understanding of Scenes through the ADE20K Dataset
- Semantic Image Segmentation via Deep Parsing Network
- Deep Learning of Representations: Looking Forward
- A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition
- Proposal-free Network for Instance-level Object Segmentation
- Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
- Instance-sensitive Fully Convolutional Networks
- Label Refinement Network for Coarse-to-Fine Semantic Segmentation
- Multi-Dimensional Recurrent Neural Networks
- Fully Convolutional Instance-aware Semantic Segmentation
- Learning Dense Convolutional Embeddings for Semantic Segmentation
- Interpretable Structure-Evolving LSTM
- Reinforcement Learning for Semantic Segmentation in Indoor Scenes
- Geometric Scene Parsing with Hierarchical LSTM
- Deep Structured Scene Parsing by Learning with Image Descriptions
- Knowledge-Guided Recurrent Neural Network Learning for Task-Oriented Action Prediction
- Progressively Diffused Networks for Semantic Image Segmentation