Deep Decision Network for Multi-class Image Classification

Murthy, Venkatesh; Singh, V. P.; Chen, Terrence; Manmatha, R.; Comanicìu, Dorin

doi:10.1109/cvpr.2016.246

Cited by 66 publications

(52 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We simply apply normalization for images using means and standard deviations in three channels. For convenience of making comparison with related works, which use NIN [15] as base model, such as HD-CNN [29], DDN [30], DualNet [31], we build a D-PCN based on NIN. We follow the setting of NIN in [30,31], and D-PCN is trained without data augmentation.…”

Section: Classification Results On Cifar-100mentioning

confidence: 99%

“…Table 1 shows performance comparisons between several works. Noted directly compared to D-PCN are [15,[29][30][31], which are all built on NIN and deploying multiple networks. And HD-CNN actually uses cropping and 10 view testing [1] as data augmentation, but it's a representative work using multiple subnetworks, for which reason it's listed here.…”

Section: Classification Results On Cifar-100mentioning

confidence: 99%

“…Speculating on how to strengthen ability of existed CNN models is a feasible approach. Several works have paid attention to that, including Bilinear CNN [28], HD-CNN [29], DDN [30] and DualNet [31], all of which resort to multiple networks. HD-CNN [29] embeds CNN into two-level category hierarchy, it separates easy classes with a coarse category classifier while distinguishing different classes using a fine classifier.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Parallel Convolutional Networks for Image Recognition via a Discriminator

Yang

Peng

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which takes integrated features from parallel networks and gives final prediction. The discriminator is core which drives parallel networks to focus on different regions and learn different representations. The corresponding training strategy is introduced to ensures utilization of discriminator. We validate D-PCN with several CNN models on benchmark datasets: CIFAR-100, and ImageNet, D-PCN enhances all models. In particular it yields state of the art performance on CIFAR-100 compared with related works. We also conduct visualization experiment on fine-grained Stanford Dogs dataset to verify our motivation. Additionally, we apply D-PCN for segmentation on PASCAL VOC 2012 and also find promotion.

show abstract

Section: Classification Results On Cifar-100mentioning

confidence: 99%

Section: Classification Results On Cifar-100mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Parallel Convolutional Networks for Image Recognition via a Discriminator

Yang

Peng

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…However, such multi-way splits are cumbersome to determine and do not improve the performance of decision trees [13]. [28] is another closely related work to ours. It uses a deep neural network to perform a hierarchical partition of the data as in decision trees while creating the clusters of confusing classes.…”

Section: Hybridization Based Classification Techniquesmentioning

confidence: 94%

Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision Surfaces

Katuwal

Suganthan

2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Both neural networks and decision trees are popular machine learning methods and are widely used to solve problems from diverse domains. These two classifiers are commonly used base classifiers in an ensemble framework. In this paper, we first present a new variant of oblique decision tree based on a linear classifier, then construct an ensemble classifier based on the fusion of a fast neural network, random vector functional link network and oblique decision trees. Random Vector Functional Link Network has an elegant closed form solution with extremely short training time. The neural network partitions each training bag (obtained using bagging) at the root level into C subsets where C is the number of classes in the dataset and subsequently, C oblique decision trees are trained on such partitions. The proposed method provides a rich insight into the data by grouping the confusing or hard to classify samples for each class and thus, provides an opportunity to employ fine-grained classification rule over the data. The performance of the ensemble classifier is evaluated on several multi-class datasets where it demonstrates a superior performance compared to other stateof-the-art classifiers.

show abstract

“…CIGN may also be compared to neural network-decision tree hybrids. [20] builds a Deep Decision Network; first classifying the data with a root network, and then using spectral clustering on the misclassified samples. New networks for each class cluster are added iteratively and trained by holding the previous networks fixed.…”

Section: Neural Network -Decision Tree Hybridsmentioning

confidence: 99%

Conditional Information Gain Networks

Biçici

Keskin

Akarun

2018

2018 24th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network models employing conditional computing are able to reduce computational requirements while achieving high representational power, with their ability to model hierarchies. We propose Conditional Information Gain Networks, which allow the feed forward deep neural networks to execute conditionally, skipping parts of the model based on the sample and the decision mechanisms inserted in the architecture. These decision mechanisms are trained using cost functions based on differentiable Information Gain, inspired by the training procedures of decision trees. These information gain based decision mechanisms are differentiable and can be trained end-to-end using a unified framework with a general cost function, covering both classification and decision losses. We test the effectiveness of the proposed method on MNIST and recently introduced Fashion MNIST datasets and show that our information gain based conditional execution approach can achieve better or comparable classification results using significantly fewer parameters, compared to standard convolutional neural network baselines.

show abstract

Deep Decision Network for Multi-class Image Classification

Cited by 66 publications

References 9 publications

Parallel Convolutional Networks for Image Recognition via a Discriminator

Parallel Convolutional Networks for Image Recognition via a Discriminator

Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision Surfaces

Conditional Information Gain Networks

Contact Info

Product

Resources

About