• Corpus ID: 215885983

Local-HDP: Interactive Open-Ended 3D Object Categorization

@article{Ayoobi2020LocalHDPIO,
  title={Local-HDP: Interactive Open-Ended 3D Object Categorization},
  author={Hamed Ayoobi and Seyed Hamidreza Mohades Kasaei and Ming Cao and Rineke Verbrugge and Bart Verheij},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.01152}
}
We introduce a nonparametric hierarchical Bayesian approach for open-ended 3D object categorization, named the Local Hierarchical Dirichlet Process (Local-HDP). This method allows an agent to learn independent topics for each category incrementally and adapt to the environment through time. Hierarchical Bayesian approaches like Latent Dirichlet Allocation (LDA) can transform low-level features to high-level conceptual topics for 3D object categorization. However, the efficiency and accuracy of… 

Figures and Tables from this paper

Open-Ended Fine-Grained 3D Object Categorization by Combining Shape and Texture Features in Multiple Colorspaces

A deep transfer learning approach to generate a scale- and pose-invariant object representation by considering shape and texture information in multiple color spaces and shows that the proposed network architecture outperformed the selected state-of-the-art in terms of object classification accuracy and scalability.

Combining Shape Features with Multiple Color Spaces in Open-Ended 3D Object Recognition

The network architecture proposed in this work expands from the OrthographicNet, an approach recently proposed by Kasaei et al., using a deep transfer learning strategy which not only meets the aforementioned requirements but additionally generates a scale and rotation-invariant reference frame for the classification of objects.

Open-Ended 3D Object Recognition using OrthographicNet and Color Information

The network architecture proposed in this work expands from the OrthographicNet, an approach recently proposed by Kasaei et al., using a deep transfer learning strategy which not only meets requirements but additionally generates a scale and rotation-invariant reference frame for the classification of objects.

References

SHOWING 1-10 OF 47 REFERENCES

Local-LDA: Open-Ended Learning of Latent Topics for 3D Object Recognition

An open-ended 3D object recognition system which concurrently learns both the object categories and the statistical features for encoding objects, and an extension of Latent Dirichlet Allocation to learn structural semantic features for each category independently.

Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition

An open-ended 3D object recognition system which concurrently learns both the object categories and the statistical features for encoding objects and an extension of Latent Dirichlet Allocation to learn structural semantic features from low-level feature co-occurrences for each category independently.

RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-View Images

A Convolutional Neural Network (CNN)-based model “RotationNet,” which takes multi-view images of an object as input and jointly estimates its pose and object category, is proposed, which achieves superior performance to the state-of-the-art methods of 3D object classification on 10- and 40-class ModelNet datasets.

Online Variational Inference for the Hierarchical Dirichlet Process

This work proposes an online variational inference algorithm for the HDP, an algorithm that is easily applicable to massive and streaming data, and lets us analyze much larger data sets.

Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework

This paper proposes a unified multiplicative framework for attribute learning that can both accurately predict attributes and learn efficient image representations and can improve the state-of-the-art performance on several widely used datasets.

The Supervised Hierarchical Dirichlet Process

We propose the supervised hierarchical Dirichlet process (sHDP), a nonparametric generative model for the joint distribution of a group of observations and a response variable directly associated

Self Paced Deep Learning for Weakly Supervised Object Detection

This paper is the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline, built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes.

Collapsed Variational Inference for HDP

This work obtains the first variational algorithm to deal with the hierarchical Dirichlet process and with hyperparameters ofDirichlet variables, and shows a significant improvement in accuracy.

Recurrent Convolutional Fusion for RGB-D Object Recognition

This work introduces a novel end-to-end architecture for RGB-D object recognition called recurrent convolutional fusion (RCFusion), which significantly outperforms state-of-the-art approaches in both the object categorization and instance recognition tasks.

Topic Modelling for Object-Based Unsupervised Classification of VHR Panchromatic Satellite Images Based on Multiscale Image Segmentation

A novel unsupervised object-based classification for VHR panchromatic satellite images using multiple segmentations via the latent Dirichlet allocation (LDA) model is presented, able to achieve scale-adaptive classification results, and improve the ability to differentiate the geo-objects with spectral overlap.