• Corpus ID: 8890823

Multi-label Image Classification with A Probabilistic Label Enhancement Model

@inproceedings{Li2014MultilabelIC,
  title={Multi-label Image Classification with A Probabilistic Label Enhancement Model},
  author={X. Li and Feipeng Zhao and Yuhong Guo},
  booktitle={UAI},
  year={2014}
}
In this paper, we present a novel probabilistic label enhancement model to tackle multi-label image classification problem. Recognizing multiple objects in images is a challenging problem due to label sparsity, appearance variations of the objects and occlusions. We propose to tackle these difficulties from a novel perspective by constructing auxiliary labels in the output space. Our idea is to exploit label combinations to enrich the label space and improve the label identification capacity in… 

Figures and Tables from this paper

Conditional Graphical Lasso for Multi-label Image Classification
TLDR
Conditional graphical Lasso (CGL) provides a unified Bayesian framework for structure and parameter learning conditioned on image features and performs competitively for multi-label image classification on benchmark datasets MULAN scene, PASCAL VOC 2007 and PASCal VOC 2012, compared with the state-of-the-art multi- label classification algorithms.
Joint Input and Output Space Learning for Multi-Label Image Classification
TLDR
A deep learning framework that incorporates flexible modules which can learn from both input and output spaces for multi-label image classification is proposed and achieves superior performance over the state-of-the-arts.
Multi-label Image Classification Model via Label Correlation Matrix
TLDR
This model generates label word vectors based on the BERT model that can describe the potential relationship between labels and combines these vectors with static statistics information on labels to construct a new label correlation matrix.
Distribution-based Label Space Transformation for Multi-label Learning
TLDR
A distribution-based label space transformation (DLST) model that has the capability to handle label set sparsity and training data sparsity in multi-label learning problems and not only achieves high classification performance but also is computationally more efficient.
Multi-Label Image Classification with Attention Mechanism and Graph Convolutional Networks
TLDR
A novel framework for multi-label image classification, which uses attention mechanism and Graph Convolutional Network (GCN) simultaneously, which can effectively improve the classification performance and is competitive with the state-of-the-art methods.
Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification
TLDR
Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance, and significantly outperforms state-of-the-arts and has strong generalization capability.
Multi-View Metric Learning for Multi-Label Image Classification
TLDR
This paper proposes a novel multi-view distance metric learning approach to dealing with the multi-label image classification problem, and attempts to concatenate multiple types of features after learning one optimal distance metric for each view, so as to obtain a better joint representation across multi- view spaces.
Reconstruction Regularized Deep Metric Learning for Multi-Label Image Classification
TLDR
A novel deep metric learning method to tackle the multi-label image classification problem by attempting to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively, to capture the relationships between image features and labels.
Learning with Latent Label Hierarchy from Incomplete Multi-Label Data
TLDR
A probabilistic model is proposed that captures the hierarchical structure and the incompleteness of the labels and an Expectation-Maximization (EM) procedure for maximum likelihood estimation is introduced.
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
TLDR
This work proposes an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships, and generates novel cross-modality attention maps which outperforms other existing state-of-the-arts methods for multi-label classification.
...
...

References

SHOWING 1-10 OF 39 REFERENCES
New Graph Structured Sparsity Model for Multi-label Image Annotations
TLDR
This paper model the label correlations using the relational graph, and proposes a novel graph structured sparse learning model to incorporate the topological constraints of relation graph in multi-label classifications to improve the annotation results.
Multi-label Classification with Output Kernels
TLDR
This work demonstrates how a state-of-the-art large margin loss for multi-label classification can be reformulated, exactly, to handle output kernels as well as input kernels and develops a projected gradient descent training procedure for this new formulation.
Correlated Label Propagation with Application to Multi-label Learning
TLDR
A novel framework for multi-label learning termed Correlated Label Propagation (CLP) that explicitly models interactions between labels in an efficient manner and leads to significant gains in precision/recall against standard techniques on two real-world computer vision tasks involving several hundred labels.
Image annotation using multi-label correlated Green's function
TLDR
A novel multi-label correlated Green's function approach is proposed to annotate images over a graph to deal with the difficulty of label assignment in most of the existing rank-based multi- label classification algorithms.
Probabilistic Multi-Label Classification with Sparse Feature Learning
TLDR
This paper forms this sparse norm regularized learning problem as a non-smooth convex optimization problem, and develops a fast proximal gradient algorithm to solve it for an optimal solution.
Annotating images and image objects using a hierarchical dirichlet process model
TLDR
A nonparametric Bayesian model which provides a generalization for multi-model latent Dirichlet allocation model (MoM-LDA) used for similar problems in the past and performs just as well as or better than the MoM- LDA model (regardless of the choice of the number of clusters) for predicting labels of objects in images containing multiple objects.
Supervised Learning of Semantic Classes for Image Annotation and Retrieval
TLDR
The supervised formulation is shown to achieve higher accuracy than various previously published methods at a fraction of their computational cost and to be fairly robust to parameter tuning.
Multi-label Multiple Kernel Learning
TLDR
The proposed learning formulation leads to a non-smooth min-max problem, which can be cast into a semi-infinite linear program (SILP) and an approximate formulation with a guaranteed error bound which involves an unconstrained convex optimization problem.
Multilabel classification via calibrated label ranking
TLDR
This work proposes a suitable extension of label ranking that incorporates the calibrated scenario and substantially extends the expressive power of existing approaches and suggests a conceptually novel technique for extending the common learning by pairwise comparison approach to the multilabel scenario, a setting previously not being amenable to the pairwise decomposition technique.
...
...