Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Information": models, code, and papers

Attentional Graph Neural Network for Parking-slot Detection

Apr 06, 2021
Chen Min, Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai

Deep learning has recently demonstrated its promising performance for vision-based parking-slot detection. However, very few existing methods explicitly take into account learning the link information of the marking-points, resulting in complex post-processing and erroneous detection. In this paper, we propose an attentional graph neural network based parking-slot detection method, which refers the marking-points in an around-view image as graph-structured data and utilize graph neural network to aggregate the neighboring information between marking-points. Without any manually designed post-processing, the proposed method is end-to-end trainable. Extensive experiments have been conducted on public benchmark dataset, where the proposed method achieves state-of-the-art accuracy. Code is publicly available at \url{}.

* IEEE Robotics and Automation Letters, vol.6, pp. 3445-3450, 2021 
* Accepted by RAL 

  Access Paper or Ask Questions

A data-driven personalized smart lighting recommender system

Apr 05, 2021
Atousa Zarindast, Jonathan Wood, Anuj Sharma

Recommender systems attempts to identify and recommend the most preferable item (product-service) to an individual user. These systems predict user interest in items based on related items, users, and the interactions between items and users. We aim to build an auto-routine and color scheme recommender system that leverages a wealth of historical data and machine learning methods. We introduce an unsupervised method to recommend a routine for lighting. Moreover, by analyzing users' daily logs, geographical location, temporal and usage information we understand user preference and predict their preferred color for lights. To do so, we cluster users based on their geographical information and usage distribution. We then build and train a predictive model within each cluster and aggregate the results. Results indicate that models based on similar users increases the prediction accuracy, with and without prior knowledge about user preferences.

  Access Paper or Ask Questions

Multitask Recalibrated Aggregation Network for Medical Code Prediction

Apr 02, 2021
Wei Sun, Shaoxiong Ji, Erik Cambria, Pekka Marttinen

Medical coding translates professionally written medical reports into standardized codes, which is an essential part of medical information systems and health insurance reimbursement. Manual coding by trained human coders is time-consuming and error-prone. Thus, automated coding algorithms have been developed, building especially on the recent advances in machine learning and deep neural networks. To solve the challenges of encoding lengthy and noisy clinical documents and capturing code associations, we propose a multitask recalibrated aggregation network. In particular, multitask learning shares information across different coding schemes and captures the dependencies between different medical codes. Feature recalibration and aggregation in shared modules enhance representation learning for lengthy notes. Experiments with a real-world MIMIC-III dataset show significantly improved predictive performance.

  Access Paper or Ask Questions

Self Regulated Learning Mechanism for Data Efficient Knowledge Distillation

Feb 14, 2021
Sourav Mishra, Suresh Sundaram

Existing methods for distillation use the conventional training approach where all samples participate equally in the process and are thus highly inefficient in terms of data utilization. In this paper, a novel data-efficient approach to transfer the knowledge from a teacher model to a student model is presented. Here, the teacher model uses self-regulation to select appropriate samples for training and identifies their significance in the process. During distillation, the significance information can be used along with the soft-targets to supervise the students. Depending on the use of self-regulation and sample significance information in supervising the knowledge transfer process, three types of distillations are proposed - significance-based, regulated, and hybrid, respectively. Experiments on benchmark datasets show that the proposed methods achieve similar performance as other state-of-the-art methods for knowledge distillation while utilizing a significantly less number of samples.

* 8 pages, 5 figures, 5 tables, 29 references 

  Access Paper or Ask Questions

Feature Sharing Cooperative Network for Semantic Segmentation

Jan 20, 2021
Ryota Ikedo, Kazuhiro Hotta

In recent years, deep neural networks have achieved high ac-curacy in the field of image recognition. By inspired from human learning method, we propose a semantic segmentation method using cooperative learning which shares the information resembling a group learning. We use two same networks and paths for sending feature maps between two networks. Two networks are trained simultaneously. By sharing feature maps, one of two networks can obtain the information that cannot be obtained by a single network. In addition, in order to enhance the degree of cooperation, we propose two kinds of methods that connect only the same layer and multiple layers. We evaluated our proposed idea on two kinds of networks. One is Dual Attention Network (DANet) and the other one is DeepLabv3+. The proposed method achieved better segmentation accuracy than the conventional single network and ensemble of networks.

* computer vision and pattern recognition 

  Access Paper or Ask Questions

Design and Implementation of Curriculum System Based on Knowledge Graph

Dec 23, 2020
Xiaobing Yu, Mike Stahr, Han Chen, Runming Yan

With the fact that the knowledge in each field in university is keeping increasing, the number of university courses is becoming larger, and the content and curriculum system is becoming much more complicated than it used to be, which bring many inconveniences to the course arrangement and analysis. In this paper, we aim to construct a method to visualize all courses based on Google Knowledge Graph. By analysing the properties of the courses and their preceding requirements, we want to extract the relationship between the precursors and the successors, so as to build the knowledge graph of the curriculum system. Using the graph database Neo4j [7] as the core aspect for data storage and display for our new curriculum system will be our approach to implement our knowledge graph. Based on this graph, the venation relationship between courses can be clearly analysed, and some difficult information can be obtained, which can help to combine the outline of courses and the need to quickly query the venation information of courses.

* 4 pages, 4 figures, accepted by ICCECE 

  Access Paper or Ask Questions

Dense Multiscale Feature Fusion Pyramid Networks for Object Detection in UAV-Captured Images

Dec 19, 2020
Yingjie Liu

Although much significant progress has been made in the research field of object detection with deep learning, there still exists a challenging task for the objects with small size, which is notably pronounced in UAV-captured images. Addressing these issues, it is a critical need to explore the feature extraction methods that can extract more sufficient feature information of small objects. In this paper, we propose a novel method called Dense Multiscale Feature Fusion Pyramid Networks(DMFFPN), which is aimed at obtaining rich features as much as possible, improving the information propagation and reuse. Specifically, the dense connection is designed to fully utilize the representation from the different convolutional layers. Furthermore, cascade architecture is applied in the second stage to enhance the localization capability. Experiments on the drone-based datasets named VisDrone-DET suggest a competitive performance of our method.

* 10 pages, 5 figures 

  Access Paper or Ask Questions

Generating Dialogue Responses from a Semantic Latent Space

Oct 04, 2020
Wei-Jen Ko, Avik Ray, Yilin Shen, Hongxia Jin

Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there are multiple possible responses to a given prompt. In this work, we hypothesize that the current models are unable to integrate information from multiple semantically similar valid responses of a prompt, resulting in the generation of generic and uninformative responses. To address this issue, we propose an alternative to the end-to-end classification on vocabulary. We learn the pair relationship between the prompts and responses as a regression task on a latent space instead. In our novel dialog generation model, the representations of semantically related sentences are close to each other on the latent space. Human evaluation showed that learning the task on a continuous space can generate responses that are both relevant and informative.

* EMNLP 2020 

  Access Paper or Ask Questions

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

Oct 04, 2020
Shiquan Yang, Rui Zhang, Sarah Erfani

End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. There are two challenges for such systems: one is how to effectively incorporate external knowledge bases (KBs) into the learning framework; the other is how to accurately capture the semantics of dialogue history. In this paper, we address these two challenges by exploiting the graph structural information in the knowledge base and in the dependency parsing tree of the dialogue. To effectively leverage the structural information in dialogue history, we propose a new recurrent cell architecture which allows representation learning on graphs. To exploit the relations between entities in KBs, the model combines multi-hop reasoning ability based on the graph structure. Experimental results show that the proposed model achieves consistent improvement over state-of-the-art models on two different task-oriented dialogue datasets.

* 11 pages, 5 figures, Accepted as an EMNLP 2020 Long Paper 

  Access Paper or Ask Questions

Spatiotemporal Modeling of Seismic Images for Acoustic Impedance Estimation

Jun 28, 2020
Ahmad Mustafa, Motaz Alfarraj, Ghassan AlRegib

Seismic inversion refers to the process of estimating reservoir rock properties from seismic reflection data. Conventional and machine learning-based inversion workflows usually work in a trace-by-trace fashion on seismic data, utilizing little to no information from the spatial structure of seismic images. We propose a deep learning-based seismic inversion workflow that models each seismic trace not only temporally but also spatially. This utilizes information-relatedness in seismic traces in depth and spatial directions to make efficient rock property estimations. We empirically compare our proposed workflow with some other sequence modeling-based neural networks that model seismic data only temporally. Our results on the SEAM dataset demonstrate that, compared to the other architectures used in the study, the proposed workflow is able to achieve the best performance, with an average $r^{2}$ coefficient of 79.77\%.

  Access Paper or Ask Questions