Objects as Context for Detecting Their Semantic Parts

We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone (+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.

• Publication year

  2017

• Venue

  2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

• Publication date

  2017-03-28

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CVPR.2018.00722
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Joint Multi-person Pose Estimation and Semantic Part Segmentation

  2017cited by this paper
• End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation

  2016cited by this paper
• Do Semantic Parts Emerge in Convolutional Neural Networks?

  2016cited by this paper
• Human Pose Estimation via Convolutional Part Heatmap Regression

  2016cited by this paper
• Semantic Object Parsing with Graph LSTM

  2016cited by this paper
• SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition

  2016influential reference
• Learning Semantic Part-Based Models from Google Images

  2016cited by this paper
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

  2016cited by this paper
• Fast R-CNN

  2015influential reference
• Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net

  2015cited by this paper
• Joint Object and Part Segmentation Using Deep Learned Potentials

  2015influential reference
• Deep Residual Learning for Image Recognition

  2015influential reference
• Context Forest for Object Class Detection

  2015cited by this paper
• Deep LAC: Deep localization, alignment and classification for fine-grained recognition

  2015cited by this paper
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

  2015cited by this paper
• Adaptive region pooling for object detection

  2015cited by this paper
• From Facial Parts Responses to Face Detection: A Deep Learning Approach

  2015cited by this paper
• Part-Stacked CNN for Fine-Grained Visual Categorization

  2015cited by this paper
• Subset feature learning for fine-grained category classification

  2015cited by this paper
• Boosting Speed and Accuracy in Deformable Part Models for Face Image in the Wild

  2015cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Part-Pair Representation for Part Localization

  2014cited by this paper
• Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts

  2014influential reference
• Semantic part segmentation using compositional model combining shape and appearance

  2014cited by this paper
• Actions and Attributes from Wholes and Parts

  2014influential reference
• ImageNet Large Scale Visual Recognition Challenge

  2014cited by this paper
• Nonparametric Part Transfer for Fine-Grained Recognition

  2014cited by this paper
• Edge Boxes: Locating Object Proposals from Edges

  2014cited by this paper
• Training Deformable Object Models for Human Detection Based on Alignment and Clustering

  2014cited by this paper
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

  2014cited by this paper
• The application of two-level attention models in deep convolutional neural network for fine-grained image classification

  2014cited by this paper
• Part Detector Discovery in Deep Convolutional Neural Networks

  2014cited by this paper
• 30Hz Object Detection with DPM V5

  2014cited by this paper
• Part-Based R-CNNs for Fine-Grained Category Detection

  2014cited by this paper
• Hypercolumns for object segmentation and fine-grained localization

  2014cited by this paper
• Context Driven Scene Parsing with Attention to Rare Classes

  2014cited by this paper
• Understanding Objects in Detail with Fine-Grained Attributes

  2014cited by this paper
• MatConvNet: Convolutional Neural Networks for MATLAB

  2014cited by this paper
• Visualizing and Understanding Convolutional Networks

  2013cited by this paper
• Fine-Grained Categorization by Alignments

  2013influential reference
• Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction

  2013cited by this paper
• Learning Collections of Part Models for Object Recognition

  2013cited by this paper
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

  2013cited by this paper
• Selective Search for Object Recognition

  2013cited by this paper
• PANDA: Pose Aligned Networks for Deep Attribute Modeling

  2013cited by this paper
• Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

  2013influential reference
• How Important Are "Deformable Parts" in the Deformable Parts Model?

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012influential reference
• Object Detection Using Strongly-Supervised Deformable Part Models

  2012influential reference
• Articulated pose estimation with parts connectivity using discriminative local oriented contours

  2012cited by this paper
• Dog Breed Classification Using Part Localization

  2012cited by this paper
• The Caltech-UCSD Birds-200-2011 Dataset

  2011influential reference
• Shared parts for deformable part-based models

  2011cited by this paper
• A coarse-to-fine approach for fast deformable object detection

  2011cited by this paper
• Scene recognition and weakly supervised object localization with deformable part-based models

  2011cited by this paper
• Articulated part-based model for joint object detection and pose estimation

  2011cited by this paper
• Measuring the Objectness of Image Windows

  2011cited by this paper
• The Pascal Visual Object Classes (VOC) Challenge

  2010cited by this paper
• Object Detection with Discriminatively Trained Part Based Models

  2010influential reference
• Detecting People Using Mutually Consistent Poselet Activations

  2010cited by this paper
• Object Recognition by Scene Alignment

  2007cited by this paper
• Histograms of oriented gradients for human detection

  2005cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes

  2003cited by this paper
• Contextual Priming for Object Detection

  2003cited by this paper
• Care of aged doctors

  1969cited by this paper

• Groundhog Grounding Large Language Models to Holistic Segmentation

  2024cites this paper
• Preventing Errors in Person Detection: A Part-Based Self-Monitoring Framework

  2023cites this paper
• DCANet: Dense Context-Aware Network for Semantic Segmentation

  2021cites this paper
• for Exploit Visual Dependency Relations for Semantic Segmentation

  2021cites this paper
• Human Parsing With Pyramidical Gather-Excite Context

  2021cites this paper
• OCNet: Object Context for Semantic Segmentation

  2021cites this paper
• Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement

  2021cites this paper
• 3D Compositional Zero-shot Learning with DeCompositional Consensus

  2021cites this paper
• OCNet: Object Context Network for Scene Parsing

  2018cites this paper
• Exploiting LSTM for Joint Object and Semantic Part Detection

  2018cites this paper
• Hierarchical semantic segmentation using modular convolutional neural networks

  2017cites this paper