Visibility Estimation via Deep Label Distribution Learning

Training Examples ◽

Label Distribution ◽

Visibility Estimation

This paper proposes an image-based visibility estimation method with deep label distribution learning. To train an accurate model for visibility estimation, it is important to obtain the precise ground truth for every image. However, the ground-truth visibility is difficult to be labeled due to its high ambiguity. To solve this problem, we associate a label distribution to each image. The label distribution contains all the possible visibilities with their probabilities. To learn from such annotation, we employ a CNN-RNN model for visibility-aware feature extraction and a conditional probability neural network for distribution prediction. Our experiment shows that labeling the image with visibility distribution can not only overcome the inaccurate annotation problem, but also boost the learning performance without the increase of training examples.

Visibility estimation via deep label distribution learning in cloud environment

Journal of Cloud Computing Advances Systems and Applications ◽

10.1186/s13677-021-00261-7 ◽

2021 ◽

Vol 10 (1) ◽

Author(s):

Mofei Song ◽

Xu Han ◽

Xiao Fan Liu ◽

Qian Li

Keyword(s):

Cloud Computing ◽

Ground Truth ◽

Learning Performance ◽

Estimation Result ◽

Cloud Environment ◽

Computational Power ◽

Computing Technique ◽

Multiple Images ◽

Label Distribution ◽

Visibility Estimation

AbstractThe visibility estimation of the environment has great research and application value in the fields of production. To estimate the visibility, we can utilize the camera to obtain some images as evidence. However, the camera only solves the image acquisition problem, and the analysis of image visibility requires strong computational power. To realize effective and efficient visibility estimation, we employ the cloud computing technique to realize high-through image analysis. Our method combines cloud computing and image-based visibility estimation into a powerful and efficient monitoring framework. To train an accurate model for visibility estimation, it is important to obtain the precise ground truth for every image. However, the ground-truth visibility is difficult to be labeled due to its high ambiguity. To solve this problem, we associate a label distribution to each image. The label distribution contains all the possible visibilities with their probabilities. To learn from such annotation, we employ a CNN-RNN model for visibility-aware feature extraction and a conditional probability neural network for distribution prediction. The estimation result can be improved by fusing the predicting results of multiple images from different views. Our experiment shows that labeling the image with visibility distribution can boost the learning performance, and our method can obtain the visibility from the image efficiently.

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence ◽

Joint Image Emotion Classification and Distribution Learning via Deep Convolutional Neural Network

10.24963/ijcai.2017/456 ◽

2017 ◽

Cited By ~ 26

Author(s):

Jufeng Yang ◽

Dongyu She ◽

Ming Sun

Keyword(s):

Neural Network ◽

Neural Networks ◽

Prior Knowledge ◽

State Of The Art ◽

Ground Truth ◽

Majority Voting ◽

Emotion Classification ◽

Voting Scheme ◽

Label Distribution ◽

Similarity Information

Visual sentiment analysis is attracting more and more attention with the increasing tendency to express emotions through visual contents. Recent algorithms in convolutional neural networks (CNNs) considerably advance the emotion classification, which aims to distinguish differences among emotional categories and assigns a single dominant label to each image. However, the task is inherently ambiguous since an image usually evokes multiple emotions and its annotation varies from person to person. In this work, we address the problem via label distribution learning (LDL) and develop a multi-task deep framework by jointly optimizing both classification and distribution prediction. While the proposed method prefers to the distribution dataset with annotations of different voters, the majority voting scheme is widely adopted as the ground truth in this area, and few dataset has provided multiple affective labels. Hence, we further exploit two weak forms of prior knowledge, which are expressed as similarity information between labels, to generate emotional distribution for each category. The experiments conducted on both distribution datasets, i.e., Emotion6, Flickr_LDL, Twitter_LDL, and the largest single emotion dataset, i.e., Flickr and Instagram, demonstrate the proposed method outperforms the state-of-the-art approaches.

End-to-end probabilistic forecasting of electricity price via convolutional neural network and label distribution learning

Energy Reports ◽

10.1016/j.egyr.2020.11.057 ◽

2020 ◽

Vol 6 ◽

pp. 1176-1183

Author(s):

Hui He ◽

Nanyan Lu ◽

Yizhi Jiang ◽

Bo Chen ◽

Runhai Jiao

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Electricity Price ◽

Probabilistic Forecasting ◽

End To End ◽

Partial Label Learning via Label Enhancement

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015557 ◽

2019 ◽

Vol 33 ◽

pp. 5557-5564 ◽

Cited By ~ 5

Author(s):

Ning Xu ◽

Jiaqi Lv ◽

Xin Geng

Keyword(s):

Predictive Model ◽

Learning Strategy ◽

Feature Space ◽

Ground Truth ◽

Learning Approaches ◽

Topological Information ◽

Common Strategy ◽

Training Examples ◽

Partial Label Learning ◽

Partial label learning aims to learn from training examples each associated with a set of candidate labels, among which only one label is valid for the training example. The common strategy to induce predictive model is trying to disambiguate the candidate label set, such as disambiguation by identifying the ground-truth label iteratively or disambiguation by treating each candidate label equally. Nonetheless, these strategies ignore considering the generalized label distribution corresponding to each instance since the generalized label distribution is not explicitly available in the training set. In this paper, a new partial label learning strategy named PL-LE is proposed to learn from partial label examples via label enhancement. Specifically, the generalized label distributions are recovered by leveraging the topological information of the feature space. After that, a multi-class predictive model is learned by fitting a regularized multi-output regressor with the generalized label distributions. Extensive experiments show that PL-LE performs favorably against state-ofthe-art partial label learning approaches.

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

Privileged label enhancement with multi-label learning

10.24963/ijcai.2020/329 ◽

2020 ◽

Author(s):

Wenfang Zhu ◽

Xiuyi Jia ◽

Weiwei Li

Keyword(s):

Prediction Model ◽

Structural Information ◽

Ground Truth ◽

Learning Model ◽

Privileged Information ◽

Enhancement Method ◽

Complex Structural ◽

Label distribution learning has attracted more and more attention in view of its more generalized ability to express the label ambiguity. However, it is much more expensive to obtain the label distribution information of the data rather than the logical labels. Thus, label enhancement is proposed to recover the label distributions from the logical labels. In this paper, we propose a novel label enhancement method by using privileged information. We first apply a multi-label learning model to implicitly capture the complex structural information between instances and generate the privileged information. Second, we adopt LUPI (learning with privileged information) paradigm to utilize the privileged information and employ RSVM+ as the prediction model. Finally, comparison experiments on 12 datasets demonstrate that our proposal can better fit the ground-truth label distributions.

Partial Multi-Label Learning with Label Distribution

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.6124 ◽

2020 ◽

Vol 34 (04) ◽

pp. 6510-6517 ◽

Cited By ~ 2

Author(s):

Ning Xu ◽

Yun-Peng Liu ◽

Xin Geng

Keyword(s):

Predictive Model ◽

Learning Strategy ◽

Feature Space ◽

Ground Truth ◽

Topological Information ◽

Common Strategy ◽

The Common ◽

Real World Datasets ◽

Training Examples ◽

Partial multi-label learning (PML) aims to learn from training examples each associated with a set of candidate labels, among which only a subset are valid for the training example. The common strategy to induce predictive model is trying to disambiguate the candidate label set, such as identifying the ground-truth label via utilizing the confidence of each candidate label or estimating the noisy labels in the candidate label sets. Nonetheless, these strategies ignore considering the essential label distribution corresponding to each instance since the label distribution is not explicitly available in the training set. In this paper, a new partial multi-label learning strategy named Pml-ld is proposed to learn from partial multi-label examples via label enhancement. Specifically, label distributions are recovered by leveraging the topological information of the feature space and the correlations among the labels. After that, a multi-class predictive model is learned by fitting a regularized multi-output regressor with the recovered label distributions. Experimental results on synthetic as well as real-world datasets clearly validate the effectiveness of Pml-ld for solving PML problems.

Multi-Branch Deformable Convolutional Neural Network with Label Distribution Learning for Fetal Brain Age Prediction

2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) ◽

10.1109/isbi45749.2020.9098553 ◽

2020 ◽

Cited By ~ 1

Author(s):

Lufan Liao ◽

Xin Zhang ◽

Fenqiang Zhao ◽

Jingjiao Lou ◽

Li Wang ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Fetal Brain ◽

Label Distribution ◽

Brain Age ◽

Age Prediction

Image Process of Rock Size Distribution Using DexiNed-Based Neural Network

Minerals ◽

10.3390/min11070736 ◽

2021 ◽

Vol 11 (7) ◽

pp. 736

Author(s):

Haijie Li ◽

Gauti Asbjörnsson ◽

Mats Lindqvist

Keyword(s):

Neural Network ◽

Size Distribution ◽

Estimation Method ◽

Ground Truth ◽

Operating Conditions ◽

Image Process ◽

Morphological Transformation ◽

The Right ◽

Crushing Plant ◽

And Control

In an aggregate crushing plant, the crusher performances will be affected by the variation from the incoming feed size distribution. Collecting accurate measurements of the size distribution on the conveyors can help both operators and control systems to make the right decisions in order to reduce overall power consumption and avoid undesirable operating conditions. In this work, a particle size distribution estimation method based on a DexiNed edge detection network, followed by the application of contour optimization, is proposed. The proposed framework was carried out in the four main steps. The first step, after image preprocessing, was to utilize a modified DexiNed convolutional neural network to predict the edge map of the rock image. Next, morphological transformation and watershed transformation from the OpenCV library were applied. Then, in the last step, the mass distribution was estimated from the pixel contour area. The accuracy and efficiency of the DexiNed method were demonstrated by comparing it with the ground-truth segmentation. The PSD estimation was validated with the laboratory screened rock samples.

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

Classification with Label Distribution Learning

10.24963/ijcai.2019/515 ◽

2019 ◽

Cited By ~ 1

Author(s):

Jing Wang ◽

Xin Geng

Keyword(s):

Information Entropy ◽

Learning Algorithm ◽

Ground Truth ◽

Classification Model ◽

Distribution Model ◽

Model Output ◽

Real Word ◽

Large Margin ◽

Label Distribution Learning (LDL) is a novel learning paradigm, aim of which is to minimize the distance between the model output and the ground-truth label distribution. We notice that, in real-word applications, the learned label distribution model is generally treated as a classification model, with the label corresponding to the highest model output as the predicted label, which unfortunately prompts an inconsistency between the training phrase and the test phrase. To solve the inconsistency, we propose in this paper a new Label Distribution Learning algorithm for Classification (LDL4C). Firstly, instead of KL-divergence, absolute loss is applied as the measure for LDL4C. Secondly, samples are re-weighted with information entropy. Thirdly, large margin classifier is adapted to boost discrimination precision. We then reveal that theoretically LDL4C seeks a balance between generalization and discrimination. Finally, we compare LDL4C with existing LDL algorithms on 17 real-word datasets, and experimental results demonstrate the effectiveness of LDL4C in classification.