scholarly journals Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer

2021 ◽  
Author(s):  
Markos Georgopoulos ◽  
James Oldfield ◽  
Mihalis A. Nicolaou ◽  
Yannis Panagakis ◽  
Maja Pantic
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
State Of The Art ◽  
Skin Tone ◽  
Training Set ◽  
Demographic Groups ◽  
Underrepresented Groups ◽  
Qualitative And Quantitative ◽  
Multi Scale ◽  
Single Attribute

AbstractDeep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard evaluation metrics and benchmarks, a surge of work has recently exposed the demographic bias that such algorithms exhibit–highlighting that accuracy does not entail fairness. Clearly, deploying biased systems under real-world settings can have grave consequences for affected populations. Indeed, learning methods are prone to inheriting, or even amplifying the bias present in a training set, manifested by uneven representation across demographic groups. In facial datasets, this particularly relates to attributes such as skin tone, gender, and age. In this work, we address the problem of mitigating bias in facial datasets by data augmentation. We propose a multi-attribute framework that can successfully transfer complex, multi-scale facial patterns even if these belong to underrepresented groups in the training set. This is achieved by relaxing the rigid dependence on a single attribute label, and further introducing a tensor-based mixing structure that captures multiplicative interactions between attributes in a multilinear fashion. We evaluate our method with an extensive set of qualitative and quantitative experiments on several datasets, with rigorous comparisons to state-of-the-art methods. We find that the proposed framework can successfully mitigate dataset bias, as evinced by extensive evaluations on established diversity metrics, while significantly improving fairness metrics such as equality of opportunity.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

scholarly journals Adversarial Training for Community Question Answer Selection Based on Multi-Scale Matching

2019 ◽  
Vol 33 ◽  
pp. 395-402
Author(s):  
Xiao Yang ◽  
Madian Khabsa ◽  
Miaosen Wang ◽  
Wei Wang ◽  
Ahmed Hassan Awadallah ◽  
...  
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Classification Problem ◽  
Classification Model ◽  
Training Set ◽  
Community Based ◽  
Multi Scale ◽  
Adversarial Training ◽  
Source Of Information ◽  
Different Levels

Community-based question answering (CQA) websites represent an important source of information. As a result, the problem of matching the most valuable answers to their corresponding questions has become an increasingly popular research topic. We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue. We employ a generative model to iteratively sample a subset of challenging negative samples to fool our classification model. Both models are alternatively optimized using REINFORCE algorithm. The proposed method is completely different from previous ones, where negative samples in training set are directly used or uniformly down-sampled. Further, we propose using Multi-scale Matching which explicitly inspects the correlation between words and ngrams of different levels of granularity. We evaluate the proposed method on SemEval 2016 and SemEval 2017 datasets and achieves state-of-the-art or similar performance.

scholarly journals Mixed Maximum Loss Design for Optic Disc and Optic Cup Segmentation with Deep Learning from Imbalanced Samples

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4401 ◽  
Author(s):  
Yong-li Xu ◽  
Shuai Lu ◽  
Han-xiong Li ◽  
Rui-rui Li
Keyword(s):  
Deep Learning ◽  
Optic Disc ◽  
Learning Strategy ◽  
State Of The Art ◽  
Loss Minimization ◽  
Training Strategy ◽  
Multi Scale ◽  
Maximum Loss ◽  
Screening Performance ◽  
Optic Cup

Glaucoma is a serious eye disease that can cause permanent blindness and is difficult to diagnose early. Optic disc (OD) and optic cup (OC) play a pivotal role in the screening of glaucoma. Therefore, accurate segmentation of OD and OC from fundus images is a key task in the automatic screening of glaucoma. In this paper, we designed a U-shaped convolutional neural network with multi-scale input and multi-kernel modules (MSMKU) for OD and OC segmentation. Such a design gives MSMKU a rich receptive field and is able to effectively represent multi-scale features. In addition, we designed a mixed maximum loss minimization learning strategy (MMLM) for training the proposed MSMKU. This training strategy can adaptively sort the samples by the loss function and re-weight the samples through data enhancement, thereby synchronously improving the prediction performance of all samples. Experiments show that the proposed method has obtained a state-of-the-art breakthrough result for OD and OC segmentation on the RIM-ONE-V3 and DRISHTI-GS datasets. At the same time, the proposed method achieved satisfactory glaucoma screening performance on the RIM-ONE-V3 and DRISHTI-GS datasets. On datasets with an imbalanced distribution between typical and rare sample images, the proposed method obtained a higher accuracy than existing deep learning methods.

MO078DEEP LEARNING DIAGNOSIS OF ANTIBODY-MEDIATED REJECTION (AMR) ON GLOMERULAR TRANSECTIONS

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
Pietro A Cicalese ◽  
Syed A Rizvi ◽  
Candice Roufosse ◽  
Ibrahim Batal ◽  
Martin Hellmich ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Interobserver Variability ◽  
Training Set ◽  
Style Transfer ◽  
Antibody Mediated Rejection ◽  
Learning Classifier ◽  
Common Causes ◽  
Level Performance ◽  
Fold Cross Validation

Abstract Background and Aims Antibody-mediated rejection (AMR) is among the most common causes for kidney transplant loss. The histological diagnosis is hampered by significant intra- and interobserver variability. Training a deep learning classifier for the recognition of AMR on glomerular transections as the most decisive compartment could establish a reliable and perfectly reproducible diagnostic method. Method We identified 48 biopsies with AMR (all positive for donor-specific antibody) and 38 biopsies without AMR according to Banff 2017 from our archive. Photographs were taken from all non-globally sclerosed glomeruli on two PAS-stained level sections, yielding a total of 1,655 images as a training set. 1,503 images could be labeled by three experienced nephropathologists conclusively as AMR or non-AMR in a blinded fashion. We trained a DenseNet-121 classifier (pre-trained on ImageNet) with basic online augmentation. In addition, we implemented StyPath++, a data augmentation algorithm that leverages a style transfer mechanism, addressing significant domain shifts in histopathology. Each sample was assigned a consensus label generated by the pathologists. Results Five-fold cross validation schemes produced a weighted glomerular level performance of 88.1%, exceeding the baseline performance by 5%. The improved generalization ability of the StyPath++ augmented model shows that it is possible to construct reliable glomerular classification algorithms with scarce datasets. Conclusion We created a deep learning classifier with excellent performance and reproducibility for the diagnosis of AMR on glomerular transections. We plan to expand the training set, including challenging cases of differential diagnoses like glomerulonephritis or other glomerulopathies. We are also interested in external clinicopathological datasets to further validate our results.

Improving multi-class Boosting-based object detection

2020 ◽  
Vol 28 (1) ◽  
pp. 81-96
Author(s):  
José Miguel Buenaposada ◽  
Luis Baumela
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Data Augmentation ◽  
Detection Performance ◽  
Significant Progress ◽  
Training Techniques ◽  
Multi Scale ◽  
Bounding Box ◽  
Open Issue ◽  
The Impact

In recent years we have witnessed significant progress in the performance of object detection in images. This advance stems from the use of rich discriminative features produced by deep models and the adoption of new training techniques. Although these techniques have been extensively used in the mainstream deep learning-based models, it is still an open issue to analyze their impact in alternative, and computationally more efficient, ensemble-based approaches. In this paper we evaluate the impact of the adoption of data augmentation, bounding box refinement and multi-scale processing in the context of multi-class Boosting-based object detection. In our experiments we show that use of these training advancements significantly improves the object detection performance.

scholarly journals A Simple Method to Train the AI Diagnosis Model of Pulmonary Nodules

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Zhehao He ◽  
Wang Lv ◽  
Jian Hu
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Pulmonary Nodules ◽  
Learning System ◽  
Pathological Diagnosis ◽  
Classification Model ◽  
Lung Nodules ◽  
Training Set ◽  
Simple Method ◽  
Test Set

Background. The differential diagnosis of subcentimetre lung nodules with a diameter of less than 1 cm has always been one of the problems of imaging doctors and thoracic surgeons. We plan to create a deep learning model for the diagnosis of pulmonary nodules in a simple method. Methods. Image data and pathological diagnosis of patients come from the First Affiliated Hospital of Zhejiang University School of Medicine from October 1, 2016, to October 1, 2019. After data preprocessing and data augmentation, the training set is used to train the model. The test set is used to evaluate the trained model. At the same time, the clinician will also diagnose the test set. Results. A total of 2,295 images of 496 lung nodules and their corresponding pathological diagnosis were selected as a training set and test set. After data augmentation, the number of training set images reached 12,510 images, including 6,648 malignant nodular images and 5,862 benign nodular images. The area under the P-R curve of the trained model is 0.836 in the classification of malignant and benign nodules. The area under the ROC curve of the trained model is 0.896 (95% CI: 78.96%~100.18%), which is higher than that of three doctors. However, the P value is not less than 0.05. Conclusion. With the help of an automatic machine learning system, clinicians can create a deep learning pulmonary nodule pathology classification model without the help of deep learning experts. The diagnostic efficiency of this model is not inferior to that of the clinician.

scholarly journals Progressively Inpainting Images Based on a Forked-Then-Fused Decoder Network

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6336
Author(s):  
Shuai Yang ◽  
Rong Huang ◽  
Fang Han
Keyword(s):  
Long Range ◽  
State Of The Art ◽  
Image Inpainting ◽  
Basic Component ◽  
Qualitative And Quantitative ◽  
Multi Scale ◽  
Art Works ◽  
Quantitative Results

Image inpainting aims to fill in corrupted regions with visually realistic and semantically plausible contents. In this paper, we propose a progressive image inpainting method, which is based on a forked-then-fused decoder network. A unit called PC-RN, which is the combination of partial convolution and region normalization, serves as the basic component to construct inpainting network. The PC-RN unit can extract useful features from the valid surroundings and can suppress incompleteness-caused interference at the same time. The forked-then-fused decoder network consists of a local reception branch, a long-range attention branch, and a squeeze-and-excitation-based fusing module. Two multi-scale contextual attention modules are deployed into the long-range attention branch for adaptively borrowing features from distant spatial positions. Progressive inpainting strategy allows the attention modules to use the previously filled region to reduce the risk of allocating wrong attention. We conduct extensive experiments on three benchmark databases: Places2, Paris StreetView, and CelebA. Qualitative and quantitative results show that the proposed inpainting model is superior to state-of-the-art works. Moreover, we perform ablation studies to reveal the functionality of each module for the image inpainting task.

scholarly journals Efficient Deep Learning Model for COVID-19 Detection in large CT images datasets: A cross-dataset analysis

2020 ◽  
Author(s):  
Pedro Silva ◽  
Eduardo Luz ◽  
Guilherme Silva ◽  
Gladston Moreira ◽  
Rodrigo Silva ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
State Of The Art ◽  
Ct Images ◽  
Critical Factors ◽  
Specific Data ◽  
Dataset Analysis ◽  
Detection And Diagnosis ◽  
Deep Learning Model ◽  
Early Detection And Diagnosis

Abstract Early detection and diagnosis are critical factors to control the COVID-19 spreading. A number of deep learning-based methodologies have been recently proposed for COVID-19 screening in CT scans as a tool to automate and help with the diagnosis. To achieve these goals, in this work, we propose a slice voting-based approach extending the EfficientNet Family of deep artificial neural networks.We also design a specific data augmentation process and transfer learning for such task.Moreover, a cross-dataset study is performed into the two largest datasets to date. The proposed method presents comparable results to the state-of-the-art methods and the highest accuracy to date on both datasets (accuracy of 87.60\% for the COVID-CT dataset and accuracy of 98.99% for the SARS-CoV-2 CT-scan dataset). The cross-dataset analysis showed that the generalization power of deep learning models is far from acceptable for the task since accuracy drops from 87.68% to 56.16% on the best evaluation scenario.These results highlighted that the methods that aim at COVID-19 detection in CT-images have to improve significantly to be considered as a clinical option and larger and more diverse datasets are needed to evaluate the methods in a realistic scenario.

scholarly journals Antimicrobial peptide identification using multi-scale convolutional network

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Xin Su ◽  
Jing Xu ◽  
Yanbin Yin ◽  
Xiongwen Quan ◽  
Han Zhang
Keyword(s):  
Deep Learning ◽  
Antimicrobial Peptide ◽  
State Of The Art ◽  
Peptide Identification ◽  
The State ◽  
Fusion Model ◽  
Learning Methods ◽  
Convolutional Network ◽  
Multi Scale ◽  
Peptide Database

Abstract Background Antibiotic resistance has become an increasingly serious problem in the past decades. As an alternative choice, antimicrobial peptides (AMPs) have attracted lots of attention. To identify new AMPs, machine learning methods have been commonly used. More recently, some deep learning methods have also been applied to this problem. Results In this paper, we designed a deep learning model to identify AMP sequences. We employed the embedding layer and the multi-scale convolutional network in our model. The multi-scale convolutional network, which contains multiple convolutional layers of varying filter lengths, could utilize all latent features captured by the multiple convolutional layers. To further improve the performance, we also incorporated additional information into the designed model and proposed a fusion model. Results showed that our model outperforms the state-of-the-art models on two AMP datasets and the Antimicrobial Peptide Database (APD)3 benchmark dataset. The fusion model also outperforms the state-of-the-art model on an anti-inflammatory peptides (AIPs) dataset at the accuracy. Conclusions Multi-scale convolutional network is a novel addition to existing deep neural network (DNN) models. The proposed DNN model and the modified fusion model outperform the state-of-the-art models for new AMP discovery. The source code and data are available at https://github.com/zhanglabNKU/APIN.

scholarly journals Attention-Based Multi-Context Guiding for Few-Shot Semantic Segmentation

2019 ◽  
Vol 33 ◽  
pp. 8441-8448 ◽  
Author(s):  
Tao Hu ◽  
Pengwan Yang ◽  
Chiliang Zhang ◽  
Gang Yu ◽  
Yadong Mu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Feature Fusion ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Research Topic ◽  
Context Information ◽  
Multi Scale ◽  
Support Set ◽  
Segmentation Task ◽  
Context Features

Few-shot learning is a nascent research topic, motivated by the fact that traditional deep learning methods require tremendous amounts of data. The scarcity of annotated data becomes even more challenging in semantic segmentation since pixellevel annotation in segmentation task is more labor-intensive to acquire. To tackle this issue, we propose an Attentionbased Multi-Context Guiding (A-MCG) network, which consists of three branches: the support branch, the query branch, the feature fusion branch. A key differentiator of A-MCG is the integration of multi-scale context features between support and query branches, enforcing a better guidance from the support set. In addition, we also adopt a spatial attention along the fusion branch to highlight context information from several scales, enhancing self-supervision in one-shot learning. To address the fusion problem in multi-shot learning, Conv-LSTM is adopted to collaboratively integrate the sequential support features to elevate the final accuracy. Our architecture obtains state-of-the-art on unseen classes in a variant of PASCAL VOC12 dataset and performs favorably against previous work with large gains of 1.1%, 1.4% measured in mIoU in the 1-shot and 5-shot setting.

Sign in / Sign up

Export Citation Format

Share Document