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:Â
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
Comparison between soft computing methods for tomato quality grading using machine vision
TL;DR: A deep stacked sparse auto-encoders (DSSAEs) method was proposed for tomato quality grading using image data directly, instead of analysing features extracted from the tomato images.
Journal ArticleDOI
Upright orientation of 3D shapes with Convolutional Networks
TL;DR: A data-driven method for 3D object upright orientation estimation using 3D Convolutional Networks (ConvNets), and the method is designed in the style of divide-and-conquer due to the interference effect, which is at least 30 times faster than existing methods.
Journal ArticleDOI
An efficient assembly retrieval method based on Hausdorff distance
TL;DR: The study reveals that the proposed method can retrieve relevant assemblies efficiently on the premise of assuring the accuracy, and a directed Hausdorff distance is proposed, which only compares the local dissimilarity.
Proceedings ArticleDOI
Time series prediction method based on Convolutional Autoencoder and LSTM
TL;DR: First, a one-dimensional convolution is used in the encoding and decoding network of the autoEncoder to extract data features and then use Long Short-Term Memory to predict, and the prediction error of convolutional autoEncoding-Long Short Term Memory (CAE and LSTM) model is significantly lower than other models.
Journal ArticleDOI
Three-dimensional texture measurement using deep learning and multi-view pavement images
TL;DR: A framework for macro-texture measurement and reconstruction using any number of pavement views based on deep CNN is presented, showing that the proposed framework performs 3D model reconstruction with satisfactory precision and stability.
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.