Open AccessPosted Content
Deep Learning Representation using Autoencoder for 3D Shape Retrieval
TLDR
This work projects 3D shapes into 2D space and uses autoencoder for feature learning on the 2D images and shows the proposed deep learning feature is complementary to conventional local image descriptors, which can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.Abstract:
We study the problem of how to build a deep learning representation for 3D shape. Deep learning has shown to be very effective in variety of visual applications, such as image classification and object detection. However, it has not been successfully applied to 3D shape recognition. This is because 3D shape has complex structure in 3D space and there are limited number of 3D shapes for feature learning. To address these problems, we project 3D shapes into 2D space and use autoencoder for feature learning on the 2D images. High accuracy 3D shape retrieval performance is obtained by aggregating the features learned on 2D images. In addition, we show the proposed deep learning feature is complementary to conventional local image descriptors. By combing the global deep learning representation and the local descriptor representation, our method can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.read more
Citations
More filters
Journal ArticleDOI
An analysis on the use of autoencoders for representation learning: Fundamentals, learning task case studies, explainability and challenges
TL;DR: This paper presents a series of learning tasks: data embedding for visualization, image denoising, semantic hashing, detection of abnormal behaviors and instance generation, and concludes that autoencoders may be the core of a possible solution to many problems which can be modeled as a transformation of the feature space.
Journal ArticleDOI
A survey of 2D shape representation: Methods, evaluations, and future research directions
TL;DR: A comprehensive survey to summarize the overall view of image-based shape representation, covering several concepts including the traditional shape descriptors, boundary and region partitioning strategies, and more advanced techniques which commonly exist in the recent studies.
Journal ArticleDOI
Automatic segmentation of left ventricle from cardiac MRI via deep learning and region constrained dynamic programming
TL;DR: A hybrid scheme combining deep learning and dynamic programming for automatic segmentation of the LV from cardiac MRI datasets is effective and robust and can compute LV functional indexes from population imaging.
Journal ArticleDOI
Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder
TL;DR: This paper proposes a novel low-level structure feature extraction for image processing based on deep neural network, stacked sparse denoising autoencoder (SSDA), and demonstrates that the features trained from natural images are not specific and can extract the structure features of infrared images.
Journal ArticleDOI
A Hybrid convolutional neural network for sketch recognition
TL;DR: This paper proposes a novel architecture, named Hybrid CNN, which is composed of A-Net and S-Net, which describe appearance information and shape information, respectively and demonstrates that the Hybrid CNN achieves competitive accuracy compared with the state-of-the-art methods.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Journal ArticleDOI
Neural networks and physical systems with emergent collective computational abilities
TL;DR: A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: 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.