Bilinear deep learning for image classification

@article{Zhong2011BilinearDL,
  title={Bilinear deep learning for image classification},
  author={Sheng-hua Zhong and Yan Liu and Yang Liu},
  journal={Proceedings of the 19th ACM international conference on Multimedia},
  year={2011}
}
  • S. Zhong, Yan Liu, Yang Liu
  • Published 2011
  • Computer Science
  • Proceedings of the 19th ACM international conference on Multimedia
Image classification is a well-known classical problem in multimedia content analysis. This paper proposes a novel deep learning model called bilinear deep belief network (BDBN) for image classification. Unlike previous image classification models, BDBN aims to provide human-like judgment by referencing the architecture of the human visual system and the procedure of intelligent perception. Therefore, the multi-layer structure of the cortex and the propagation of information in the visual areas… Expand
Semiconducting bilinear deep learning for incomplete image recognition
TLDR
Owing to exploiting the embedding information according to the reliable features rather than any completion of missing features, the proposed semiconducting bilinear deep belief networks has demonstrated outstanding recognition ability on two standard datasets and one constructed dataset, comparing with both incomplete image recognition techniques and existing deep learning models. Expand
Field Effect Deep Networks for Image Recognition with Incomplete Data
TLDR
A novel second-order deep architecture with the Field Effect Restricted Boltzmann Machine is designed, which models the reliability of the delivered information according to the availability of the features and can jointly determine the classification boundary and estimate the missing features. Expand
An Improved Bilinear Deep Belief Network Algorithm for Image Classification
TLDR
A novel image recognition method based on the improved BDBN (Bilinear Deep Belief Network) model, optimized with a MKL (Multiple Kernel Learning) strategy, which can improve the accuracy of traditional B DBN methods by up to 2.8%, and the accuracy is superior to some methods in the literature. Expand
Multi-view semi-supervised learning for image classification
TLDR
A novel multi-view semi-supervised learning framework which leverages the information contained in pseudo-labeled images to improve the prediction performance of image classification using multiple views of an image. Expand
Image classification via multi-view model
TLDR
A novel multi-view semi-supervised learning framework which leverages the information contained in pseudo-labeled images to improve the prediction performance of image classification using multiple views of an image. Expand
A Survey on the New Generation of Deep Learning in Image Processing
TLDR
This survey provides four deep learning model series, which includes CNN series, GAN series, ELM-RVFL series, and other series, for comprehensive understanding towards the analytical techniques of image processing field, clarify the most important advancements and shed some light on future studies. Expand
Image Blur Classification and Parameter Identification Using Two-stage Deep Belief Networks
TLDR
This paper proposes a Two-stage system using Deep Belief Networks to first classify the blur type and then identify its parameters, and a semi-supervised DBN is trained to project the input samples in a discriminative feature space, and then classify those features. Expand
Image annotation via deep neural network
  • C. Sun, S. Zhu, Zhe Shi
  • Computer Science
  • 2015 14th IAPR International Conference on Machine Vision Applications (MVA)
  • 2015
TLDR
A multimodal deep learning framework is proposed that aims to optimally integrate multiple deep neural networks pretrained with convolutional neural networks to annotate multilabel image annotation. Expand
Deep neural network based image annotation
TLDR
A multimodal deep learning framework that aims to optimally integrate multiple deep neural networks pretrained with convolutional neural networks to improve annotation performance and find optimal combination of diverse modalities simultaneously in a coherent process is proposed. Expand
Self-paced dictionary learning for image classification
TLDR
A self-paced dictionary learning algorithm is proposed, which uses the easy samples to train the dictionary first, and then iteratively introduces more complex samples in the remaining training procedure until the entire training data are all easy samples. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 59 REFERENCES
Discriminative Deep Belief Networks for image classification
TLDR
Experiments show that DDBN outperforms most semi-supervised algorithm and deep learning techniques, especially for the hard classification tasks. Expand
Randomized Clustering Forests for Image Classification
TLDR
This work introduces Extremely Randomized Clustering Forests-ensembles of randomly created clustering trees-and shows that they provide more accurate results, much faster training and testing, and good resistance to background clutter. Expand
Hierarchical image feature extraction and classification
TLDR
The experimental result on two datasets shows that the proposed hierarchical feature extraction combined with the novel hierarchical classification achieves better accuracy performance than conventional non-hierarchical classification methods, and hence conventional hierarchical methods as well. Expand
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
TLDR
The convolutional deep belief network is presented, a hierarchical generative model which scales to realistic image sizes and is translation-invariant and supports efficient bottom-up and top-down probabilistic inference. Expand
Linear spatial pyramid matching using sparse coding for image classification
TLDR
An extension of the SPM method is developed, by generalizing vector quantization to sparse coding followed by multi-scale spatial max pooling, and a linear SPM kernel based on SIFT sparse codes is proposed, leading to state-of-the-art performance on several benchmarks by using a single type of descriptors. Expand
Image Classification using Random Forests and Ferns
TLDR
It is shown that selecting the ROI adds about 5% to the performance and, together with the other improvements, the result is about a 10% improvement over the state of the art for Caltech-256. Expand
Semi-supervised learning of multi-factor models for face de-identification
TLDR
This paper proposes a new multi-factor framework which unifies linear, bilinear, and quadratic models and describes a new fitting algorithm which jointly estimates all model parameters and shows that it outperforms the standard alternating algorithm. Expand
In defense of Nearest-Neighbor based image classification
TLDR
It is argued that two practices commonly used in image classification methods, have led to the inferior performance of NN-based image classifiers: Quantization of local image descriptors (used to generate "bags-of-words ", codebooks) and Computation of 'image-to-image' distance, instead of ' image- to-class' distance. Expand
A Fast Learning Algorithm for Deep Belief Nets
TLDR
A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. Expand
Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines
TLDR
A low-rank approximation to this interaction tensor that uses a sum of factors, each of which is a three-way outer product, which allows efficient learning of transformations between larger image patches and demonstrates the learning of optimal filter pairs from various synthetic and real image sequences. Expand
...
1
2
3
4
5
...