Fully Connected Deep Structured Networks
arXiv:1503.02351
Abstract
Convolutional neural networks with many layers have recently been shown to achieve excellent results on many high-level tasks such as image classification, object detection and more recently also semantic segmentation. Particularly for semantic segmentation, a two-stage procedure is often employed. Hereby, convolutional networks are trained to provide good local pixel-wise features for the second step being traditionally a more global graphical model. In this work we unify this two-stage process into a single joint training algorithm. We demonstrate our method on the semantic image segmentation task and show encouraging results on the challenging PASCAL VOC 2012 dataset.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Natural Language Processing (almost) from Scratch
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
- Show and Tell: A Neural Image Caption Generator
- Deep Visual-Semantic Alignments for Generating Image Descriptions
Cited by in corpus (17)
- Adversarial Networks for the Detection of Aggressive Prostate Cancer
- Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
- Learning Deep Structured Models
- Semantic Facial Expression Editing using Autoencoded Flow
- Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
- Learning Affinity via Spatial Propagation Networks
- InstanceCut: from Edges to Instances with MultiCut
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
- Learning Person Trajectory Representations for Team Activity Analysis
- Nonlinear Markov Random Fields Learned via Backpropagation
- Structured Prediction using cGANs with Fusion Discriminator
- Value of Temporal Dynamics Information in Driving Scene Segmentation
- Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling
- Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
- Progressively Diffused Networks for Semantic Image Segmentation
- Scaling Matters in Deep Structured-Prediction Models
- Efficient Continuous Relaxations for Dense CRF