Learning Structured Inference Neural Networks with Label Relations

Abstract

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels that depict high level abstraction or a set of labels that reveal attributes. Such categorization at different concept layers can be modeled with label graphs encoding label information. In this paper, we exploit this rich information with a state-of-art deep learning framework, and propose a generic structured model that leverages diverse label relations to improve image classification performance. Our approach employs a novel stacked label prediction neural network, capturing both inter-level and intra-level label semantics. We evaluate our method on benchmark image datasets, and empirical results illustrate the efficacy of our model.

arXiv commentConference on Computer Vision and Pattern Recognition(CVPR) 2016

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Going Deeper with Convolutions
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Deep Convolutional Ranking for Multilabel Image Annotation
• Fully Connected Deep Structured Networks
• Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition
• Probabilistic Label Relation Graphs with Ising Models

Cited by in corpus (4)

• Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
• Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
• LabelBank: Revisiting Global Perspectives for Semantic Segmentation
• Image Annotation using Multi-Layer Sparse Coding