Convolutional Feature Masking for Joint Object and Stuff Segmentation
arXiv:1412.1283 · doi:10.1109/CVPR.2015.7299025
Abstract
The topic of semantic segmentation has witnessed considerable progress due to the powerful features learned by convolutional neural networks (CNNs). The current leading approaches for semantic segmentation exploit shape information by extracting CNN features from masked image regions. This strategy introduces artificial boundaries on the images and may impact the quality of the extracted features. Besides, the operations on the raw image domain require to compute thousands of networks on a single image, which is time-consuming. In this paper, we propose to exploit shape information via masking convolutional features. The proposal segments (e.g., super-pixels) are treated as masks on the convolutional feature maps. The CNN features of segments are directly masked out from these maps and used to train classifiers for recognition. We further propose a joint method to handle objects and "stuff" (e.g., grass, sky, water) in the same framework. State-of-the-art results are demonstrated on benchmarks of PASCAL VOC and new PASCAL-CONTEXT, with a compelling computational speed.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
References in corpus (5)
Cited by in corpus (97)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Conditional Random Fields as Recurrent Neural Networks
- Fully Convolutional Networks for Semantic Segmentation
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- Semantic Instance Segmentation with a Discriminative Loss Function
- Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
- Path Aggregation Network for Instance Segmentation
- Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
- Residual Attention Network for Image Classification
- W-Net: A Deep Model for Fully Unsupervised Image Segmentation
- Semantic Understanding of Scenes through the ADE20K Dataset
- Per-Pixel Classification is Not All You Need for Semantic Segmentation
- DeeperLab: Single-Shot Image Parser
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Deep Contrast Learning for Salient Object Detection
- Learning to Fuse Things and Stuff
- Efficient piecewise training of deep structured models for semantic segmentation
- 3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- Makeup like a superstar: Deep Localized Makeup Transfer Network
- Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
- Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
- One-Shot Instance Segmentation
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
- Adaptive binarization based on fuzzy integrals
- Training Deep Networks with Structured Layers by Matrix Backpropagation
- Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
- Deep Learning For Computer Vision Tasks: A review
- COCO-Stuff: Thing and Stuff Classes in Context
- Learning non-maximum suppression
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
- Object Detection Networks on Convolutional Feature Maps
- Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
- PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
- Accelerating Very Deep Convolutional Networks for Classification and Detection
- Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
- Transformer-Unet: Raw Image Processing with Unet
- InstanceCut: from Edges to Instances with MultiCut
- Hypercolumns for Object Segmentation and Fine-grained Localization
- Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
- UPSNet: A Unified Panoptic Segmentation Network
- LabelBank: Revisiting Global Perspectives for Semantic Segmentation
- Learning Dense Convolutional Embeddings for Semantic Segmentation
- Iterative Instance Segmentation
- CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
- Learning to Segment Every Thing
- Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
- Scene Parsing with Global Context Embedding
- Deep GrabCut for Object Selection
- Pose2Seg: Detection Free Human Instance Segmentation
- Exploring Context with Deep Structured models for Semantic Segmentation
- PolyTransform: Deep Polygon Transformer for Instance Segmentation
- Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels
- BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation
- Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
- Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
- PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding
- Semantically-Guided Video Object Segmentation
- Boundary-aware Instance Segmentation
- Improved Image Boundaries for Better Video Segmentation
- Bidirectional Graph Reasoning Network for Panoptic Segmentation
- Re-ranking Object Proposals for Object Detection in Automatic Driving
- Surveillance Video Parsing with Single Frame Supervision
- Dense Recurrent Neural Networks for Scene Labeling
- End-to-end detection-segmentation network with ROI convolution
- Classifying a specific image region using convolutional nets with an ROI mask as input
- Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
- Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
- Recognizing Scenes from Novel Viewpoints
- Neuron-level Selective Context Aggregation for Scene Segmentation
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
- Pixelwise Instance Segmentation with a Dynamically Instantiated Network
- Visual Semantic Information Pursuit: A Survey
- Hard Pixel Mining for Depth Privileged Semantic Segmentation
- Bipartite Conditional Random Fields for Panoptic Segmentation
- S4Net: Single Stage Salient-Instance Segmentation
- Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
- Deep Object Co-segmentation via Spatial-Semantic Network Modulation
- Object Detection with Mask-based Feature Encoding
- Cognitive Analysis of 360 degree Surround Photos
- STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
- A convnet for non-maximum suppression
- Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
- S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation
- Framework-agnostic Semantically-aware Global Reasoning for Segmentation
- Task-driven Semantic Coding via Reinforcement Learning
- Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation
- Content-Aware Convolutional Neural Networks
- Class Correlation affects Single Object Localization using Pre-trained ConvNets
- Structured Learning of Tree Potentials in CRF for Image Segmentation
- Non-parametric spatially constrained local prior for scene parsing on real-world data
- Spatial Sampling Network for Fast Scene Understanding