- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Stereo-Matching Network for Structured Light
摘要： Recently, deep learning has been widely applied in binocular stereo matching for depth acquisition, which has led to an immense increase of accuracy. However, little attention has been paid to the structured light ?eld. In this letter, a network for structured light is proposed to extract effective matching features for depth acquisition. The proposed network promotes the Siamese network by considering receptive ?elds of different scales and assigning proper weights to the corresponding features, which is achieved by combining pyramid-pooling structure with the squeeze-and-excitation network into the Siamese network for feature extraction and weight calculations, respectively. For network training and testing, a structured-light dataset with amended ground truths is generated by projecting a random pattern into the existing binocular stereo dataset. Experiments demonstrate that the proposed network is capable of real-time depth acquisition, and it provides superior depth maps using structured light.
关键词： SLNet,stereo matching,Structured light,siamese network
更新于2025-09-23 15:23:52
-
Class Agnostic Image Common Object Detection
摘要： Learning similarity of two images is an important problem in computer vision and has many potential applications. Most of previous works focus on generating image similarities in three aspects: global feature distance computing, local feature matching and image concepts comparison. However, the task of directly detecting class agnostic common objects from two images has not been studied before, which goes one step further to capture image similarities at region level. In this paper, we propose an end-to-end Image Common Object Detection Network (CODN) to detect class agnostic common objects from two images. The proposed method consists of two main modules: locating module and matching module. The locating module generates candidate proposals of each two images. The matching module learns the similarities of the candidate proposal pairs from two images, and re?nes the bounding boxes of the candidate proposals. The learning procedure of CODN is implemented in an integrated way and a multi-task loss is designed to guarantee both region localization and common object matching. Experiments are conducted on PASCAL VOC 2007 and COCO 2014 datasets. Experimental results validate the effectiveness of the proposed method.
关键词： Common object detection,relation network,siamese network
更新于2025-09-23 15:22:29
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Adversarial Domain Adaptation with a Domain Similarity Discriminator for Semantic Segmentation of Urban Areas
摘要： Existing semantic segmentation models of urban areas have shown to perform well in a supervised setting. However, collecting lots of annotated images from each city to train such models is time-consuming or difficult. In addition, when transferring the segmentation model from the trained city (source domain) to an unseen city (target domain), the performance will largely degrade due to the domain shift. For this reason, we propose a domain adaptation method with a domain similarity discriminator to eliminate such domain shift in the framework of adversarial learning. Contrary to the single-input adversarial network, our domain similarity discriminator, which consists of a Siamese network, is able to measure the similarity of the pairwise-input data. In this way, we can use more information about the pairwise-input to measure the similarity between different distributions so as to address the problem of domain shift. Experimental results demonstrate that our approach outperforms the competing methods on three different cities.
关键词： domain adaptation,urban areas,semantic segmentation,domain shift,Siamese network
更新于2025-09-23 15:22:29
-
Dynamic spectrum matching with one-shot learning
摘要： Convolutional neural networks (CNN) have been shown to provide a good solution for classification problems that utilize data obtained from vibrational spectroscopy. Moreover, CNNs are capable of identifying substances from noisy spectra without the need for additional preprocessing. However, their application in practical spectroscopy is restricted due to two reasons. First the effectiveness of classification using CNNs diminishes rapidly when only a small number of spectra per substance are available for training (which is a typical situation in real applications). Secondly, to accommodate new, previously unseen, substance classes the network must be retrained which is computationally intensive. Here we address these issues by reformulating a multi-class classification problem with a large number of classes to a binary classification problem for which the available data is sufficient for representation learning. Hence, we define the learning task as identifying pairs of inputs as belonging to the same class or different classes. We achieve this using a Siamese convolutional neural network. A novel sampling strategy is proposed to address the imbalance problem in training the Siamese network. The trained network can classify samples of previously unseen substance classes using just a single reference sample (termed as one-shot learning in the machine learning community). Our results on three independent Raman datasets demonstrate much better accuracy than other practical systems to date, while allowing effortless updates of the system’s database with new substance classes.
关键词： Spectrum Matching,Siamese Network,Convolutional Neural Networks,One-shot Learning
更新于2025-09-23 15:19:57
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Discriminative Learning of Point Cloud Feature Descriptors Based on Siamese Network
摘要： It is challenging to direct extract the feature descriptors of the object in the point cloud, although deep learning has been widely used with the classification and detection in the point cloud, those methods hidden feature presentation in the network. Since the point cloud scanned by the Laser Scanner usually have different point density, unordered and even the different occlusion, which go beyond the reach of hand-crafted descriptors, e.g. FPH, FPFH, VFH, ROPS. In this paper, we aim to direct extract the feature descriptors of the point cloud object through the raw point cloud. Inspired by the recent success of the Siamese networks[6], PointNet[7] and PointNet++[8], we propose a novel network to direct extract the feature descriptors of the whole point cloud object. We train our network with the Euclidean distance as the loss function which reflects feature descriptors similarity. The experiment object datasets were acquired by Mobile Laser Scanning (MLS) system which contains 6 categories. Experiment result shows that our network has a robust generalization, which can well direct extract the feature descriptors of the whole point cloud object.
关键词： Point cloud,mobile laser scanning,feature description,siamese network
更新于2025-09-10 09:29:36