Feedforward semantic segmentation with zoom-out features

Abstract

We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent. These regions are obtained by "zooming out" from the superpixel all the way to scene-level resolution. This approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead superpixels are classified by a feedforward multilayer network. Our architecture achieves new state of the art performance in semantic segmentation, obtaining 64.4% average accuracy on the PASCAL VOC 2012 test set.

References in corpus (2)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Return of the Devil in the Details: Delving Deep into Convolutional Nets

Cited by in corpus (29)

• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• ParseNet: Looking Wider to See Better
• Fully Convolutional Networks for Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Pyramid Scene Parsing Network
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Examining the Impact of Blur on Recognition by Convolutional Networks
• DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation
• PixelNet: Representation of the pixels, by the pixels, and for the pixels
• Learning a Discriminative Feature Network for Semantic Segmentation
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• Colorization as a Proxy Task for Visual Understanding
• Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
• Deeply Learning the Messages in Message Passing Inference
• Improving Fully Convolution Network for Semantic Segmentation
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• Visualizing and Understanding Deep Texture Representations
• Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
• Deep Structured Scene Parsing by Learning with Image Descriptions
• Superpixel Convolutional Networks using Bilateral Inceptions
• Semantic Segmentation with Boundary Neural Fields
• High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits
• Automatic Real-time Background Cut for Portrait Videos
• Fully Convolutional Network for Melanoma Diagnostics
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• Constrained Convolutional Neural Networks for Weakly Supervised Segmentation