Towards a Reliable Evaluation of Local Interpretation Methods

The growing use of deep neural networks in critical applications is making interpretability urgently to be solved. Local interpretation methods are the most prevalent and accepted approach for understanding and interpreting deep neural networks. How to effectively evaluate the local interpretation methods is challenging. To address this question, a unified evaluation framework is proposed, which assesses local interpretation methods from three dimensions: accuracy, persuasibility and class discriminativeness. Specifically, in order to assess correctness, we designed an interactive user feature annotation tool to provide ground truth for local interpretation methods. To verify the usefulness of the interpretation method, we iteratively display part of the interpretation results, and then ask users whether they agree with the category information. At the same time, we designed and built a set of evaluation data sets with a rich hierarchical structure. Surprisingly, one finding is that the existing visual interpretation methods cannot satisfy all evaluation dimensions at the same time, and each has its own shortcomings.

Download Full-text

Adversarial Erasing method based on graph neural network

Journal of Physics Conference Series ◽

10.1088/1742-6596/2083/4/042083 ◽

2021 ◽

Vol 2083 (4) ◽

pp. 042083

Author(s):

Shuhan Liu

Keyword(s):

Neural Network ◽

Neural Networks ◽

Loss Function ◽

Deep Neural Networks ◽

Ground Truth ◽

Semantic Segmentation ◽

Data Sets ◽

Recent Developments ◽

Weakly Supervised ◽

Network Weight

Abstract Semantic segmentation is a traditional task that requires a large number of pixel-level ground truth label data sets, which is time-consuming and expensive. Recent developments in weakly-supervised settings have shown that reasonable performance can be obtained using only image-level labels. Classification is often used as an agent task to train deep neural networks and extract attention maps from them. The classification task only needs less supervision information to obtain the most discriminative part of the object. For this purpose, we propose a new end-to-end counter-wipe network. Compared with the baseline network, we propose a method to apply the graph neural network to obtain the first CAM. It is proposed to train the joint loss function to avoid the network weight sharing and cause the network to fall into a saddle point. Our experiments on the Pascal VOC2012 dataset show that 64.9% segmentation performance is obtained, which is an improvement of 2.1% compared to our baseline.

Download Full-text

Enhanced Fusion of Deep Neural Networks for Classification of Benchmark High-Resolution Image Data Sets

IEEE Geoscience and Remote Sensing Letters ◽

10.1109/lgrs.2018.2839092 ◽

2018 ◽

Vol 15 (9) ◽

pp. 1451-1455 ◽

Cited By ~ 23

Author(s):

Grant J. Scott ◽

Kyle C. Hagan ◽

Richard A. Marcum ◽

James Alex Hurt ◽

Derek T. Anderson ◽

...

Keyword(s):

Neural Networks ◽

High Resolution ◽

Deep Neural Networks ◽

Image Data ◽

Data Sets ◽

Resolution Image ◽

High Resolution Image

Download Full-text

Evaluation of Deep Learning-Based Neural Network Methods for Cloud Detection and Segmentation

Energies ◽

10.3390/en14196156 ◽

2021 ◽

Vol 14 (19) ◽

pp. 6156

Author(s):

Stefan Hensel ◽

Marin B. Marinov ◽

Michael Koch ◽

Dimitar Arnaudov

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Data Sets ◽

Cloud Detection ◽

Camera System ◽

Data Set ◽

Network Methods ◽

Segmentation Approach ◽

Coverage Prediction ◽

Short Time

This paper presents a systematic approach for accurate short-time cloud coverage prediction based on a machine learning (ML) approach. Based on a newly built omnidirectional ground-based sky camera system, local training and evaluation data sets were created. These were used to train several state-of-the-art deep neural networks for object detection and segmentation. For this purpose, the camera-generated a full hemispherical image every 30 min over two months in daylight conditions with a fish-eye lens. From this data set, a subset of images was selected for training and evaluation according to various criteria. Deep neural networks, based on the two-stage R-CNN architecture, were trained and compared with a U-net segmentation approach implemented by CloudSegNet. All chosen deep networks were then evaluated and compared according to the local situation.

Download Full-text

A New Deep Learning Calibration Method Enhances Genome-Based Prediction of Continuous Crop Traits

Frontiers in Genetics ◽

10.3389/fgene.2021.798840 ◽

2021 ◽

Vol 12 ◽

Author(s):

Osval A. Montesinos-López ◽

Abelardo Montesinos-López ◽

Brandon A. Mosqueda-González ◽

Alison R. Bentley ◽

Morten Lillemo ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Plant Breeding ◽

Deep Neural Networks ◽

Reference Population ◽

Calibration Method ◽

Data Sets ◽

Simple Method ◽

Continuous Response ◽

Predicting Performance

Genomic selection (GS) has the potential to revolutionize predictive plant breeding. A reference population is phenotyped and genotyped to train a statistical model that is used to perform genome-enabled predictions of new individuals that were only genotyped. In this vein, deep neural networks, are a type of machine learning model and have been widely adopted for use in GS studies, as they are not parametric methods, making them more adept at capturing nonlinear patterns. However, the training process for deep neural networks is very challenging due to the numerous hyper-parameters that need to be tuned, especially when imperfect tuning can result in biased predictions. In this paper we propose a simple method for calibrating (adjusting) the prediction of continuous response variables resulting from deep learning applications. We evaluated the proposed deep learning calibration method (DL_M2) using four crop breeding data sets and its performance was compared with the standard deep learning method (DL_M1), as well as the standard genomic Best Linear Unbiased Predictor (GBLUP). While the GBLUP was the most accurate model overall, the proposed deep learning calibration method (DL_M2) helped increase the genome-enabled prediction performance in all data sets when compared with the traditional DL method (DL_M1). Taken together, we provide evidence for extending the use of the proposed calibration method to evaluate its potential and consistency for predicting performance in the context of GS applied to plant breeding.

Download Full-text

Modified Deep Neural Networks for Dog Breeds Identification

10.20944/preprints201812.0232.v1 ◽

2018 ◽

Cited By ~ 1

Author(s):

Aydin Ayanzadeh ◽

Sahand Vahidnia

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

State Of The Art ◽

The State ◽

Fine Tuning ◽

Test Accuracy ◽

Data Sets ◽

Data Set

In this paper, we leverage state of the art models on Imagenet data-sets. We use the pre-trained model and learned weighs to extract the feature from the Dog breeds identification data-set. Afterwards, we applied fine-tuning and dataaugmentation to increase the performance of our test accuracy in classification of dog breeds datasets. The performance of the proposed approaches are compared with the state of the art models of Image-Net datasets such as ResNet-50, DenseNet-121, DenseNet-169 and GoogleNet. we achieved 89.66% , 85.37% 84.01% and 82.08% test accuracy respectively which shows thesuperior performance of proposed method to the previous works on Stanford dog breeds datasets.

Download Full-text

Particle-Based Fluid Surface Rendering with Neural Networks

10.24132/csrn.2021.3101.26 ◽

2021 ◽

Author(s):

Viktória Burkus ◽

Attila Kárpáti ◽

László Szécsi

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Ground Truth ◽

Fluid Simulation ◽

Image Manipulation ◽

Surface Rendering ◽

Fluid Surface ◽

Image Pairs ◽

The Cost

Surface reconstruction for particle-based fluid simulation is a computational challenge on par with the simula- tion itself. In real-time applications, splatting-style rendering approaches based on forward rendering of particle impostors are prevalent, but they suffer from noticeable artifacts. In this paper, we present a technique that combines forward rendering simulated features with deep-learning image manipulation to improve the rendering quality of splatting-style approaches to be perceptually similar to ray tracing solutions, circumventing the cost, complexity, and limitations of exact fluid surface rendering by replacing it with the flat cost of a neural network pass. Our solution is based on the idea of training generative deep neural networks with image pairs consisting of cheap particle impostor renders and ground truth high quality ray-traced images.

Download Full-text

Interactive Artistic Multi-style Transfer

International Journal of Computational Intelligence Systems ◽

10.1007/s44196-021-00021-0 ◽

2021 ◽

Vol 14 (1) ◽

Author(s):

Xiaohui Wang ◽

Yiran Lyu ◽

Junfeng Huang ◽

Ziying Wang ◽

Jingyan Qin

Keyword(s):

Neural Networks ◽

Image Processing ◽

Deep Neural Networks ◽

Subjective Evaluation ◽

User Interaction ◽

Evaluation Framework ◽

Transfer System ◽

Style Transfer ◽

Artistic Style ◽

Artistic Styles

AbstractArtistic style transfer is to render an image in the style of another image, which is a challenge problem in both image processing and arts. Deep neural networks are adopted to artistic style transfer and achieve remarkable success, such as AdaIN (adaptive instance normalization), WCT (whitening and coloring transforms), MST (multimodal style transfer), and SEMST (structure-emphasized multimodal style transfer). These algorithms modify the content image as a whole using only one style and one algorithm, which is easy to cause the foreground and background to be blurred together. In this paper, an iterative artistic multi-style transfer system is built to edit the image with multiple styles by flexible user interaction. First, a subjective evaluation experiment with art professionals is conducted to build an open evaluation framework for style transfer, including the universal evaluation questions and personalized answers for ten typical artistic styles. Then, we propose the interactive artistic multi-style transfer system, in which an interactive image crop tool is designed to cut a content image into several parts. For each part, users select a style image and an algorithm from AdaIN, WCT, MST, and SEMST by referring to the characteristics of styles and algorithms summarized by the evaluation experiments. To obtain richer results, the system provides a semantic-based parameter adjustment mode and the function of preserving colors of content image. Finally, case studies show the effectiveness and flexibility of the system.

Download Full-text

SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification

Remote Sensing ◽

10.3390/rs12203358 ◽

2020 ◽

Vol 12 (20) ◽

pp. 3358

Author(s):

Vasileios Syrris ◽

Ondrej Pesek ◽

Pierre Soille

Keyword(s):

Neural Networks ◽

Image Classification ◽

Supervised Classification ◽

Deep Neural Networks ◽

Satellite Image ◽

Data Retrieval ◽

Remote Sensing Image ◽

Training Data ◽

Data Sets ◽

Remote Sensing Image Classification

Automatic supervised classification with complex modelling such as deep neural networks requires the availability of representative training data sets. While there exists a plethora of data sets that can be used for this purpose, they are usually very heterogeneous and not interoperable. In this context, the present work has a twofold objective: (i) to describe procedures of open-source training data management, integration, and data retrieval, and (ii) to demonstrate the practical use of varying source training data for remote sensing image classification. For the former, we propose SatImNet, a collection of open training data, structured and harmonized according to specific rules. For the latter, two modelling approaches based on convolutional neural networks have been designed and configured to deal with satellite image classification and segmentation.

Download Full-text

Artificial Intelligence Explained for Nonexperts

Seminars in Musculoskeletal Radiology ◽

10.1055/s-0039-3401041 ◽

2020 ◽

Vol 24 (01) ◽

pp. 003-011 ◽

Cited By ~ 1

Author(s):

Narges Razavian ◽

Florian Knoll ◽

Krzysztof J. Geras

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

Clinical Practice ◽

Medical Imaging ◽

Deep Neural Networks ◽

Large Data ◽

Large Data Sets ◽

Natural Images ◽

Data Sets ◽

Current State

AbstractArtificial intelligence (AI) has made stunning progress in the last decade, made possible largely due to the advances in training deep neural networks with large data sets. Many of these solutions, initially developed for natural images, speech, or text, are now becoming successful in medical imaging. In this article we briefly summarize in an accessible way the current state of the field of AI. Furthermore, we highlight the most promising approaches and describe the current challenges that will need to be solved to enable broad deployment of AI in clinical practice.

Download Full-text

Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection

mSphere ◽

10.1128/msphere.00836-20 ◽

2020 ◽

Vol 5 (5) ◽

Author(s):

Artur Yakimovich ◽

Moona Huttunen ◽

Jerzy Samolej ◽

Barbara Clough ◽

Nagisa Yoshida ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

Network Evolution ◽

Great Promise ◽

Data Sets ◽

Imaging Data ◽

Data Set ◽

Novel Strategy

ABSTRACT The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified data sets for rapid network evolution. Here, we present a novel strategy, termed “mimicry embedding,” for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets. IMPORTANCE In biology, the use of deep neural networks (DNNs) for analysis of pathogen infection is hampered by a lack of large verified data sets needed for rapid network evolution. Artificial neural networks detect handwritten digits with high precision thanks to large data sets, such as MNIST, that allow nearly unlimited training. Here, we developed a novel strategy we call mimicry embedding, which allows artificial intelligence (AI)-based analysis of variable pathogen-host data sets. We show that deep learning can be used to detect and classify single pathogens based on small differences.

Download Full-text