scholarly journals Object Detection based Deep Unsupervised Hashing

2019 ◽  
Author(s):  
Rong-Cheng Tu ◽  
Xian-Ling Mao ◽  
Bo-Si Feng ◽  
Shu-ying Yu
Keyword(s):  
Image Retrieval ◽  
Object Detection ◽  
Large Scale ◽  
Unlabeled Data ◽  
Retrieval Task ◽  
Detection Model ◽  
Label Information ◽  
Semantic Label ◽  
Large Scale Image Retrieval ◽  
Public Datasets

Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performance by utilizing semantic label information. Intuitively, for unlabeled data, it will improve the performance of unsupervised hashing methods if we can first mine some supervised semantic 'label information' from unlabeled data and then incorporate the 'label information' into the training process. Thus, in this paper, we propose a novel Object Detection based Deep Unsupervised Hashing method (ODDUH). Specifically, a pre-trained object detection model is utilized to mining supervised 'label information', which is used to guide the learning process to generate high-quality hash codes. Extensive experiments on two public datasets demonstrate that the proposed method outperforms the state-of-the-art unsupervised hashing methods in the image retrieval task.

scholarly journals Progressive Generative Hashing for Image Retrieval

2018 ◽  
Author(s):  
Yuqing Ma ◽  
Yue He ◽  
Fan Ding ◽  
Sheng Hu ◽  
Jun Li ◽  
...  
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Generative Adversarial Networks ◽  
Learning Capacity ◽  
Deep Hashing ◽  
Adversarial Networks ◽  
Label Information ◽  
Semantic Label ◽  
Large Scale Image Retrieval ◽  
Open Question

Recent years have witnessed the success of the emerging hashing techniques in large-scale image retrieval. Owing to the great learning capacity, deep hashing has become one of the most promising solutions, and achieved attractive performance in practice. However, without semantic label information, the unsupervised deep hashing still remains an open question. In this paper, we propose a novel progressive generative hashing (PGH) framework to help learn a discriminative hashing network in an unsupervised way. Very different from existing studies, it first treats the hash codes as a kind of semantic condition for the similar image generation, and simultaneously feeds the original image and its codes into the generative adversarial networks (GANs). The real images together with the synthetic ones can further help train a discriminative hashing network based on a triplet loss. By iteratively inputting the learnt codes into the hash conditioned GANs, we can progressively enable the hashing network to discover the semantic relations. Extensive experiments on the widely-used image datasets demonstrate that PGH can significantly outperforms state-of-the-art unsupervised hashing methods.

Simhash for Large Scale Image Retrieval

2014 ◽  
Vol 651-653 ◽  
pp. 2197-2200
Author(s):  
Qin Zhen Guo ◽  
Zhi Zeng ◽  
Shu Wu Zhang ◽  
Xiao Feng ◽  
Hu Guan
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Original Data ◽  
Locality Sensitive Hashing ◽  
Neighborhood Structure ◽  
Retrieval Task ◽  
Visual Words ◽  
Feature Vectors ◽  
Representation Method ◽  
Large Scale Image Retrieval

Due to its fast query speed and reduced storage cost, hashing, which tries to learn binary code representation for data with the expectation of preserving the neighborhood structure in the original data space, has been widely used in a large variety of applications like image retrieval. For most existing image retrieval methods with hashing, there are two main steps: describe images with feature vectors, and then use hashing methods to encode the feature vectors. In this paper, we make two research contributions. First, we creatively propose to use simhash which can be intrinsically combined with the popular image representation method, Bag-of-visual-words (BoW) for image retrieval. Second, we novelly incorporate “locality-sensitive” hashing into simhash to take the correlation of the visual words of BoW into consideration to make similar visual words have similar fingerprint. Extensive experiments have verified the superiority of our method over some state-of-the-art methods for image retrieval task.

scholarly journals Deep Learning Triplet Ordinal Relation Preserving Binary Code for Remote Sensing Image Retrieval Task

2021 ◽  
Vol 13 (23) ◽  
pp. 4786
Author(s):  
Zhen Wang ◽  
Nannan Wu ◽  
Xiaohan Yang ◽  
Bingqi Yan ◽  
Pingping Liu
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Binary Code ◽  
Satellite Observation ◽  
Cross Entropy ◽  
Retrieval Task ◽  
Search Tasks ◽  
Low Dimensional

As satellite observation technology rapidly develops, the number of remote sensing (RS) images dramatically increases, and this leads RS image retrieval tasks to be more challenging in terms of speed and accuracy. Recently, an increasing number of researchers have turned their attention to this issue, as well as hashing algorithms, which map real-valued data onto a low-dimensional Hamming space and have been widely utilized to respond quickly to large-scale RS image search tasks. However, most existing hashing algorithms only emphasize preserving point-wise or pair-wise similarity, which may lead to an inferior approximate nearest neighbor (ANN) search result. To fix this problem, we propose a novel triplet ordinal cross entropy hashing (TOCEH). In TOCEH, to enhance the ability of preserving the ranking orders in different spaces, we establish a tensor graph representing the Euclidean triplet ordinal relationship among RS images and minimize the cross entropy between the probability distribution of the established Euclidean similarity graph and that of the Hamming triplet ordinal relation with the given binary code. During the training process, to avoid the non-deterministic polynomial (NP) hard problem, we utilize a continuous function instead of the discrete encoding process. Furthermore, we design a quantization objective function based on the principle of preserving triplet ordinal relation to minimize the loss caused by the continuous relaxation procedure. The comparative RS image retrieval experiments are conducted on three publicly available datasets, including UC Merced Land Use Dataset (UCMD), SAT-4 and SAT-6. The experimental results show that the proposed TOCEH algorithm outperforms many existing hashing algorithms in RS image retrieval tasks.

Deep Learning Based Active Monitoring for Anti-collision between Vessels and Bridges

2019 ◽  
Author(s):  
Limu Chen ◽  
Ye Xia ◽  
Dexiong Pan ◽  
Chengbin Wang
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Object Detection ◽  
Large Scale ◽  
Data Augmentation ◽  
Information Support ◽  
Single Shot ◽  
Active Monitoring ◽  
Detection Model ◽  
Comparison Results

<p>Deep-learning based navigational object detection is discussed with respect to active monitoring system for anti-collision between vessel and bridge. Motion based object detection method widely used in existing anti-collision monitoring systems is incompetent in dealing with complicated and changeable waterway for its limitations in accuracy, robustness and efficiency. The video surveillance system proposed contains six modules, including image acquisition, detection, tracking, prediction, risk evaluation and decision-making, and the detection module is discussed in detail. A vessel-exclusive dataset with tons of image samples is established for neural network training and a SSD (Single Shot MultiBox Detector) based object detection model with both universality and pertinence is generated attributing to tactics of sample filtering, data augmentation and large-scale optimization, which make it capable of stable and intelligent vessel detection. Comparison results with conventional methods indicate that the proposed deep-learning method shows remarkable advantages in robustness, accuracy, efficiency and intelligence. In-situ test is carried out at Songpu Bridge in Shanghai, and the results illustrate that the method is qualified for long-term monitoring and providing information support for further analysis and decision making.</p>

Sign in / Sign up

Export Citation Format

Share Document