Meta-learning Based Relation and Representation Learning Networks for Single-image Deraining

2021 ◽  
pp. 108124
Author(s):  
Xinjian Gao ◽  
Yang Wang ◽  
Jun Cheng ◽  
Mingliang Xu ◽  
Meng Wang
Keyword(s):  
Representation Learning ◽  
Learning Networks ◽  
Single Image ◽  
Meta Learning

Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis

2021 ◽  
Author(s):  
Yong Feng ◽  
Jinglong Chen ◽  
Tianci Zhang ◽  
Shuilong He ◽  
Enyong Xu ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Learning Networks ◽  
Meta Learning

An Applicative Survey on Few-Shot Learning

2021 ◽  
Vol 15 ◽  
Author(s):  
Jianwei Zhang ◽  
Xubin Zhang ◽  
Lei Lv ◽  
Yining Di ◽  
Wei Chen
Keyword(s):  
Large Scale ◽  
Representation Learning ◽  
Language Models ◽  
Data Sets ◽  
Research Directions ◽  
Large Scale Data ◽  
Cross Domain ◽  
Meta Learning ◽  
Definition Of ◽  
Future Work

Background: Learning discriminative representation from large-scale data sets has made a breakthrough in decades. However, it is still a thorny problem to generate representative embedding from limited examples, for example, a class containing only one image. Recently, deep learning-based Few-Shot Learning (FSL) has been proposed. It tackles this problem by leveraging prior knowledge in various ways. Objective: In this work, we review recent advances of FSL from the perspective of high-dimensional representation learning. The results of the analysis can provide insights and directions for future work. Methods: We first present the definition of general FSL. Then we propose a general framework for the FSL problem and give the taxonomy under the framework. We survey two FSL directions: learning policy and meta-learning. Results: We review the advanced applications of FSL, including image classification, object detection, image segmentation and other tasks etc., as well as the corresponding benchmarks to provide an overview of recent progress. Conclusion: FSL needs to be further studied in medical images, language models, and reinforcement learning in future work. In addition, cross-domain FSL, successive FSL, and associated FSL are more challenging and valuable research directions.

Disentangled Representation Learning and Enhancement Network for Single Image De-Raining

2021 ◽  
Author(s):  
Guoqing Wang ◽  
Changming Sun ◽  
Xing Xu ◽  
Jingjing Li ◽  
Zheng Wang ◽  
...  
Keyword(s):  
Representation Learning ◽  
Single Image

scholarly journals Dependence Representation Learning with Convolutional Neural Networks and 2D Histograms

2020 ◽  
Vol 10 (3) ◽  
pp. 955
Author(s):  
Taejun Kim ◽  
Han-joon Kim
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Classification Accuracy ◽  
Visual Representations ◽  
Representation Learning ◽  
Single Image ◽  
Feature Generation ◽  
Average Classification Accuracy ◽  
Scatter Plots ◽  
Better Than

Researchers frequently use visualizations such as scatter plots when trying to understand how random variables are related to each other, because a single image represents numerous pieces of information. Dependency measures have been widely used to automatically detect dependencies, but these measures only take into account a few types of data, such as the strength and direction of the dependency. Based on advances in the applications of deep learning to vision, we believe that convolutional neural networks (CNNs) can come to understand dependencies by analyzing visualizations, as humans do. In this paper, we propose a method that uses CNNs to extract dependency representations from 2D histograms. We carried out three sorts of experiments and found that CNNs can learn from visual representations. In the first experiment, we used a synthetic dataset to show that CNNs can perfectly classify eight types of dependency. Then, we showed that CNNs can predict correlations based on 2D histograms of real datasets and visualize the learned dependency representation space. Finally, we applied our method and demonstrated that it performs better than the AutoLearn feature generation algorithm in terms of average classification accuracy, while generating half as many features.

scholarly journals Predicting Traffic Congestion Evolution: A Deep Meta Learning Approach

2021 ◽  
Author(s):  
Yidan Sun ◽  
Guiyuan Jiang ◽  
Siew Kei Lam ◽  
Peilan He
Keyword(s):  
Traffic Congestion ◽  
Multiple Scales ◽  
Representation Learning ◽  
Impact Factors ◽  
Learning Framework ◽  
Temporal Correlations ◽  
Heterogeneous Features ◽  
Multiple Paths ◽  
Meta Learning ◽  
Road Segments

Many efforts are devoted to predicting congestion evolution using propagation patterns that are mined from historical traffic data. However, the prediction quality is limited to the intrinsic properties that are present in the mined patterns. In addition, these mined patterns frequently fail to sufficiently capture many realistic characteristics of true congestion evolution (e.g., asymmetric transitivity, local proximity). In this paper, we propose a representation learning framework to characterize and predict congestion evolution between any pair of road segments (connected via single or multiple paths). Specifically, we build dynamic attributed networks (DAN) to incorporate both dynamic and static impact factors while preserving dynamic topological structures. We propose a Deep Meta Learning Model (DMLM) for learning representations of road segments which support accurate prediction of congestion evolution. DMLM relies on matrix factorization techniques and meta-LSTM modules to exploit temporal correlations at multiple scales, and employ meta-Attention modules to merge heterogeneous features while learning the time-varying impacts of both dynamic and static features. Compared to all state-of-the-art methods, our framework achieves significantly better prediction performance on two congestion evolution behaviors (propagation and decay) when evaluated using real-world dataset.

scholarly journals Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images

2021 ◽  
Author(s):  
Wentao Chen ◽  
Chenyang Si ◽  
Wei Wang ◽  
Liang Wang ◽  
Zilei Wang ◽  
...  
Keyword(s):  
State Of The Art ◽  
Representation Learning ◽  
Data Scarcity ◽  
Inductive Bias ◽  
Shot Classification ◽  
Learning Scheme ◽  
Augmentation Strategy ◽  
Meta Learning ◽  
Supervised Methods ◽  
Unsupervised Methods

Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class. One way to alleviate this problem is to acquire a strong inductive bias via meta-learning on similar tasks. In this paper, we show that such inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transferable representations among seen and unseen classes. Specifically, we propose a novel part-based self-supervised representation learning scheme to learn transferable representations by maximizing the similarity of an image to its discriminative part. To mitigate the overfitting in few-shot classification caused by data scarcity, we further propose a part augmentation strategy by retrieving extra images from a base dataset. We conduct systematic studies on miniImageNet and tieredImageNet benchmarks. Remarkably, our method yields impressive results, outperforming the previous best unsupervised methods by 7.74% and 9.24% under 5-way 1-shot and 5-way 5-shot settings, which are comparable with state-of-the-art supervised methods.

Sign in / Sign up

Export Citation Format

Share Document