Photo-Realistic Image Dehazing and Verifying Networks via Complementary Adversarial Learning

Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze model estimation process requires very high computational complexity. To solve this problem by directly estimating the radiance of the haze images, we present a novel dehazing and verifying network (DVNet). In the dehazing procedure, we enhanced the clean images by using a correction network (CNet), which uses the ground truth to learn the haze network. Haze images are then restored through a haze network (HNet). Furthermore, a verifying method verifies the error of both CNet and HNet using a self-supervised learning method. Finally, the proposed complementary adversarial learning method can produce results more naturally. Note that the proposed discriminator and generators (HNet & CNet) can be learned via an unpaired dataset. Overall, the proposed DVNet can generate a better dehazed result than state-of-the-art approaches under various hazy conditions. Experimental results show that the DVNet outperforms state-of-the-art dehazing methods in most cases.

Download Full-text

Joint Entity and Event Extraction with Generative Adversarial Imitation Learning

Data Intelligence ◽

10.1162/dint_a_00014 ◽

2019 ◽

Vol 1 (2) ◽

pp. 99-120 ◽

Cited By ~ 6

Author(s):

Tongtao Zhang ◽

Heng Ji ◽

Avirup Sil

Keyword(s):

State Of The Art ◽

Ground Truth ◽

Event Extraction ◽

Imitation Learning ◽

Learning Method ◽

Inverse Reinforcement Learning ◽

Generative Adversarial Network ◽

Adversarial Network ◽

The Difference ◽

New Framework

We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties (rewards) are expected to be diverse. We utilize discriminators to estimate proper rewards according to the difference between the labels committed by the ground-truth (expert) and the extractor (agent). Our experiments demonstrate that the proposed framework outperforms state-of-the-art methods.

Download Full-text

Image Aesthetic Assessment Assisted by Attributes through Adversarial Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.3301679 ◽

2019 ◽

Vol 33 ◽

pp. 679-686 ◽

Cited By ~ 3

Author(s):

Bowen Pan ◽

Shangfei Wang ◽

Qisheng Jiang

Keyword(s):

State Of The Art ◽

Ground Truth ◽

Training Data ◽

Privileged Information ◽

Adversarial Learning ◽

Deep Network ◽

Feature Representations ◽

The Aesthetic ◽

Label Distribution ◽

Representation Level

The inherent connections among aesthetic attributes and aesthetics are crucial for image aesthetic assessment, but have not been thoroughly explored yet. In this paper, we propose a novel image aesthetic assessment assisted by attributes through both representation-level and label-level. The attributes are used as privileged information, which is only required during training. Specifically, we first propose a multitask deep convolutional rating network to learn the aesthetic score and attributes simultaneously. The attributes are explored to construct better feature representations for aesthetic assessment through multi-task learning. After that, we introduce a discriminator to distinguish the predicted attributes and aesthetics of the multi-task deep network from the ground truth label distribution embedded in the training data. The multi-task deep network wants to output aesthetic score and attributes as close to the ground truth labels as possible. Thus the deep network and the discriminator compete with each other. Through adversarial learning, the attributes are explored to enforce the distribution of the predicted attributes and aesthetics to converge to the ground truth label distribution. Experimental results on two benchmark databases demonstrate the superiority of the proposed method to state of the art work.

Download Full-text

Adversarial-Learned Loss for Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5757 ◽

2020 ◽

Vol 34 (04) ◽

pp. 3521-3528

Author(s):

Minghao Chen ◽

Shuai Zhao ◽

Haifeng Liu ◽

Deng Cai

Keyword(s):

Domain Adaptation ◽

State Of The Art ◽

Confusion Matrix ◽

Ground Truth ◽

Adversarial Learning ◽

Label Method ◽

Model Predictions ◽

Novel Method ◽

Remarkable Progress ◽

Made In

Recently, remarkable progress has been made in learning transferable representation across domains. Previous works in domain adaptation are majorly based on two techniques: domain-adversarial learning and self-training. However, domain-adversarial learning only aligns feature distributions between domains but does not consider whether the target features are discriminative. On the other hand, self-training utilizes the model predictions to enhance the discrimination of target features, but it is unable to explicitly align domain distributions. In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA). We first analyze the pseudo-label method, a typical self-training method. Nevertheless, there is a gap between pseudo-labels and the ground truth, which can cause incorrect training. Thus we introduce the confusion matrix, which is learned through an adversarial manner in ALDA, to reduce the gap and align the feature distributions. Finally, a new loss function is auto-constructed from the learned confusion matrix, which serves as the loss for unlabeled target samples. Our ALDA outperforms state-of-the-art approaches in four standard domain adaptation datasets. Our code is available at https://github.com/ZJULearning/ALDA.

Download Full-text

Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty

Remote Sensing ◽

10.3390/rs12122026 ◽

2020 ◽

Vol 12 (12) ◽

pp. 2026 ◽

Cited By ~ 1

Author(s):

Ellen Bowler ◽

Peter T. Fretwell ◽

Geoffrey French ◽

Michal Mackiewicz

Keyword(s):

Deep Learning ◽

Network Performance ◽

Cross Validation ◽

State Of The Art ◽

Ground Truth ◽

Training Dataset ◽

Learning Approaches ◽

Wildlife Species ◽

Training Schemes ◽

Very High

Many wildlife species inhabit inaccessible environments, limiting researchers ability to conduct essential population surveys. Recently, very high resolution (sub-metre) satellite imagery has enabled remote monitoring of certain species directly from space; however, manual analysis of the imagery is time-consuming, expensive and subjective. State-of-the-art deep learning approaches can automate this process; however, often image datasets are small, and uncertainty in ground truth labels can affect supervised training schemes and the interpretation of errors. In this paper, we investigate these challenges by conducting both manual and automated counts of nesting Wandering Albatrosses on four separate islands, captured by the 31 cm resolution WorldView-3 sensor. We collect counts from six observers, and train a convolutional neural network (U-Net) using leave-one-island-out cross-validation and different combinations of ground truth labels. We show that (1) interobserver variation in manual counts is significant and differs between the four islands, (2) the small dataset can limit the networks ability to generalise to unseen imagery and (3) the choice of ground truth labels can have a significant impact on our assessment of network performance. Our final results show the network detects albatrosses as accurately as human observers for two of the islands, while in the other two misclassifications are largely caused by the presence of noise, cloud cover and habitat, which was not present in the training dataset. While the results show promise, we stress the importance of considering these factors for any study where data is limited and observer confidence is variable.

Download Full-text

PENERAPAN METODE COOPERATIVE LEARNING TIPE BERPASANGAN UNTUK MENINGKATKAN KEMAMPUAN TEKNIK DASAR BERMAIN KASTI DI KELAS V.A SDN 002 PANTAI CERMIN KABUPATEN KAMPAR

JURNAL PAJAR (Pendidikan dan Pengajaran) ◽

10.33578/pjr.v2i3.5542 ◽

2018 ◽

Vol 2 (3) ◽

pp. 429

Author(s):

Abd. Mulud

Keyword(s):

Action Research ◽

Data Collection ◽

Cooperative Learning ◽

Learning Method ◽

Initial Test ◽

Basic Technique ◽

Average Ability ◽

Student Activity ◽

Data Collection Instrument ◽

Very High

This research is motivated by the low ability of basic technique of playing the students' grate V.A SDN 002Pantai Cermin Kabupaten Kampar. This study aims to improve the basic techniques of playing kasti throughcooperative learning methods paired type students class V.A SDN 002 Pantai Cermin Kampar District. Thesubjects of this study are students of class V.A SDN 002 Pantai Cermin Kabupaten Kampar with the number ofstudents as many as 28 people. The form of research is classroom action research. The instrument of thisresearch consisted of performance instrument and data collection instrument in the form of observation sheet ofteacher activity and student activity. The basic technique ability to play with cooperative method of paired typelearning in VA VAN 002 Pantai Cermin Kabupaten Kabupaten Kampar average of basic technique ability toplay the students' census on the initial test is categorized less with percentage 48,9%, in cycle I increase to68,4% with sufficient category whereas in cycle II the average ability of students is categorized very high with90.8% percentage. The cassical completeness specified in this study that 80% of students have been declaredthoroughly achieved. The conclusion of this research is the application of cooperative learning method pair typecan improve basic technique of playing kasti.

Download Full-text

G-Tric: generating three-way synthetic datasets with triclustering solutions

BMC Bioinformatics ◽

10.1186/s12859-020-03925-4 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

João Lobo ◽

Rui Henriques ◽

Sara C. Madeira

Keyword(s):

State Of The Art ◽

Synthetic Data ◽

Ground Truth ◽

Real Data ◽

Three Dimensions ◽

Additional Advantage ◽

Urban Dynamics ◽

Data Generator ◽

Real World Datasets ◽

Synthetic Datasets

Abstract Background Three-way data started to gain popularity due to their increasing capacity to describe inherently multivariate and temporal events, such as biological responses, social interactions along time, urban dynamics, or complex geophysical phenomena. Triclustering, subspace clustering of three-way data, enables the discovery of patterns corresponding to data subspaces (triclusters) with values correlated across the three dimensions (observations $$\times$$ × features $$\times$$ × contexts). With increasing number of algorithms being proposed, effectively comparing them with state-of-the-art algorithms is paramount. These comparisons are usually performed using real data, without a known ground-truth, thus limiting the assessments. In this context, we propose a synthetic data generator, G-Tric, allowing the creation of synthetic datasets with configurable properties and the possibility to plant triclusters. The generator is prepared to create datasets resembling real 3-way data from biomedical and social data domains, with the additional advantage of further providing the ground truth (triclustering solution) as output. Results G-Tric can replicate real-world datasets and create new ones that match researchers needs across several properties, including data type (numeric or symbolic), dimensions, and background distribution. Users can tune the patterns and structure that characterize the planted triclusters (subspaces) and how they interact (overlapping). Data quality can also be controlled, by defining the amount of missing, noise or errors. Furthermore, a benchmark of datasets resembling real data is made available, together with the corresponding triclustering solutions (planted triclusters) and generating parameters. Conclusions Triclustering evaluation using G-Tric provides the possibility to combine both intrinsic and extrinsic metrics to compare solutions that produce more reliable analyses. A set of predefined datasets, mimicking widely used three-way data and exploring crucial properties was generated and made available, highlighting G-Tric’s potential to advance triclustering state-of-the-art by easing the process of evaluating the quality of new triclustering approaches.

Download Full-text

COVID-19 infection map generation and detection from chest X-ray images

Health Information Science and Systems ◽

10.1007/s13755-021-00146-8 ◽

2021 ◽

Vol 9 (1) ◽

Author(s):

Aysen Degerli ◽

Mete Ahishali ◽

Mehmet Yamac ◽

Serkan Kiranyaz ◽

Muhammad E. H. Chowdhury ◽

...

Keyword(s):

State Of The Art ◽

Ground Truth ◽

Clinical Use ◽

X Ray ◽

Learning Techniques ◽

Map Generation ◽

Severity Grading ◽

Chest X Ray ◽

Novel Method ◽

Aided Diagnosis

AbstractComputer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human–machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

Download Full-text

Critical Aspects of Person Counting and Density Estimation

Journal of Imaging ◽

10.3390/jimaging7020021 ◽

2021 ◽

Vol 7 (2) ◽

pp. 21

Author(s):

Roland Perko ◽

Manfred Klopschitz ◽

Alexander Almer ◽

Peter M. Roth

Keyword(s):

Density Estimation ◽

Network Architecture ◽

Reference Data ◽

State Of The Art ◽

Limit State ◽

Ground Truth ◽

Data Sets ◽

Ground Truth Generation ◽

Baseline Approach ◽

Critical Aspects

Many scientific studies deal with person counting and density estimation from single images. Recently, convolutional neural networks (CNNs) have been applied for these tasks. Even though often better results are reported, it is often not clear where the improvements are resulting from, and if the proposed approaches would generalize. Thus, the main goal of this paper was to identify the critical aspects of these tasks and to show how these limit state-of-the-art approaches. Based on these findings, we show how to mitigate these limitations. To this end, we implemented a CNN-based baseline approach, which we extended to deal with identified problems. These include the discovery of bias in the reference data sets, ambiguity in ground truth generation, and mismatching of evaluation metrics w.r.t. the training loss function. The experimental results show that our modifications allow for significantly outperforming the baseline in terms of the accuracy of person counts and density estimation. In this way, we get a deeper understanding of CNN-based person density estimation beyond the network architecture. Furthermore, our insights would allow to advance the field of person density estimation in general by highlighting current limitations in the evaluation protocols.

Download Full-text

Can Computers Outperform Humans in Detecting User Zone-Outs? Implications for Intelligent Interfaces

ACM Transactions on Computer-Human Interaction ◽

10.1145/3481889 ◽

2022 ◽

Vol 29 (2) ◽

pp. 1-33

Author(s):

Nigel Bosch ◽

Sidney K. D'Mello

Keyword(s):

Operating Characteristic ◽

State Of The Art ◽

Characteristic Curve ◽

Ground Truth ◽

Mind Wandering ◽

High Stakes ◽

Machine Learning Model ◽

Improve Accuracy ◽

Comparable Accuracy ◽

Operating Characteristic Curve

The ability to identify whether a user is “zoning out” (mind wandering) from video has many HCI (e.g., distance learning, high-stakes vigilance tasks). However, it remains unknown how well humans can perform this task, how they compare to automatic computerized approaches, and how a fusion of the two might improve accuracy. We analyzed videos of users’ faces and upper bodies recorded 10s prior to self-reported mind wandering (i.e., ground truth) while they engaged in a computerized reading task. We found that a state-of-the-art machine learning model had comparable accuracy to aggregated judgments of nine untrained human observers (area under receiver operating characteristic curve [AUC] = .598 versus .589). A fusion of the two (AUC = .644) outperformed each, presumably because each focused on complementary cues. Furthermore, adding more humans beyond 3–4 observers yielded diminishing returns. We discuss implications of human–computer fusion as a means to improve accuracy in complex tasks.

Download Full-text

Estimating Efforts and Success of Symmetry-Seeing Machines by Use of Synthetic Data

Symmetry ◽

10.3390/sym11020227 ◽

2019 ◽

Vol 11 (2) ◽

pp. 227

Author(s):

Eckart Michaelsen ◽

Stéphane Vujasinovic

Keyword(s):

Extraction Method ◽

Input Data ◽

State Of The Art ◽

Recognition Performance ◽

Human Subjects ◽

Synthetic Data ◽

Ground Truth ◽

Comparative Test ◽

Real Imagery ◽

Dominant Part

Representative input data are a necessary requirement for the assessment of machine-vision systems. For symmetry-seeing machines in particular, such imagery should provide symmetries as well as asymmetric clutter. Moreover, there must be reliable ground truth with the data. It should be possible to estimate the recognition performance and the computational efforts by providing different grades of difficulty and complexity. Recent competitions used real imagery labeled by human subjects with appropriate ground truth. The paper at hand proposes to use synthetic data instead. Such data contain symmetry, clutter, and nothing else. This is preferable because interference with other perceptive capabilities, such as object recognition, or prior knowledge, can be avoided. The data are given sparsely, i.e., as sets of primitive objects. However, images can be generated from them, so that the same data can also be fed into machines requiring dense input, such as multilayered perceptrons. Sparse representations are preferred, because the author’s own system requires such data, and in this way, any influence of the primitive extraction method is excluded. The presented format allows hierarchies of symmetries. This is important because hierarchy constitutes a natural and dominant part in symmetry-seeing. The paper reports some experiments using the author’s Gestalt algebra system as symmetry-seeing machine. Additionally included is a comparative test run with the state-of-the-art symmetry-seeing deep learning convolutional perceptron of the PSU. The computational efforts and recognition performance are assessed.

Download Full-text