scholarly journals Learning from Web Data Using Adversarial Discriminative Neural Networks for Fine-Grained Classification

2019 ◽  
Vol 33 ◽  
pp. 273-280 ◽  
Author(s):  
Xiaoxiao Sun ◽  
Liyi Chen ◽  
Jufeng Yang
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
State Of The Art ◽  
Training Data ◽  
Web Data ◽  
Fine Grained ◽  
Learning Framework ◽  
Attractive Option ◽  
Public Datasets ◽  
Noisy Labels

Fine-grained classification is absorbed in recognizing the subordinate categories of one field, which need a large number of labeled images, while it is expensive to label these images. Utilizing web data has been an attractive option to meet the demands of training data for convolutional neural networks (CNNs), especially when the well-labeled data is not enough. However, directly training on such easily obtained images often leads to unsatisfactory performance due to factors such as noisy labels. This has been conventionally addressed by reducing the noise level of web data. In this paper, we take a fundamentally different view and propose an adversarial discriminative loss to advocate representation coherence between standard and web data. This is further encapsulated in a simple, scalable and end-to-end trainable multi-task learning framework. We experiment on three public datasets using large-scale web data to evaluate the effectiveness and generalizability of the proposed approach. Extensive experiments demonstrate that our approach performs favorably against the state-of-the-art methods.

scholarly journals A Two-Stream Mutual Attention Network for Semi-Supervised Biomedical Segmentation with Noisy Labels

2019 ◽  
Vol 33 ◽  
pp. 4578-4585 ◽  
Author(s):  
Shaobo Min ◽  
Xuejin Chen ◽  
Zheng-Jun Zha ◽  
Feng Wu ◽  
Yongdong Zhang
Keyword(s):  
Supervised Learning ◽  
State Of The Art ◽  
Training Data ◽  
Attention Network ◽  
Attention Model ◽  
Learning Framework ◽  
Propagation Analysis ◽  
Supervised Methods ◽  
Multi Level ◽  
Noisy Labels

Learning-based methods suffer from a deficiency of clean annotations, especially in biomedical segmentation. Although many semi-supervised methods have been proposed to provide extra training data, automatically generated labels are usually too noisy to retrain models effectively. In this paper, we propose a Two-Stream Mutual Attention Network (TSMAN) that weakens the influence of back-propagated gradients caused by incorrect labels, thereby rendering the network robust to unclean data. The proposed TSMAN consists of two sub-networks that are connected by three types of attention models in different layers. The target of each attention model is to indicate potentially incorrect gradients in a certain layer for both sub-networks by analyzing their inferred features using the same input. In order to achieve this purpose, the attention models are designed based on the propagation analysis of noisy gradients at different layers. This allows the attention models to effectively discover incorrect labels and weaken their influence during parameter updating process. By exchanging multi-level features within two-stream architecture, the effects of noisy labels in each sub-network are reduced by decreasing the noisy gradients. Furthermore, a hierarchical distillation is developed to provide reliable pseudo labels for unlabelded data, which further boosts the performance of TSMAN. The experiments using both HVSMR 2016 and BRATS 2015 benchmarks demonstrate that our semi-supervised learning framework surpasses the state-of-the-art fully-supervised results.

scholarly journals Transfer Learning for COVID-19 Pneumonia Detection and Classification in Chest X-ray Images

2020 ◽  
Author(s):  
Iason Katsamenis ◽  
Eftychios Protopapadakis ◽  
Athanasios Voulodimos ◽  
Anastasios Doulamis ◽  
Nikolaos Doulamis
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Bacterial Pneumonia ◽  
Large Scale ◽  
Training Data ◽  
Classification Models ◽  
Automated Diagnosis ◽  
X Ray ◽  
Learning Framework ◽  
Chest X Ray

We introduce a deep learning framework that can detect COVID-19 pneumonia in thoracic radiographs, as well as differentiate it from bacterial pneumonia infection. Deep classification models, such as convolutional neural networks (CNNs), require large-scale datasets in order to be trained and perform properly. Since the number of X-ray samples related to COVID-19 is limited, transfer learning (TL) appears as the go-to method to alleviate the demand for training data and develop accurate automated diagnosis models. In this context, networks are able to gain knowledge from pretrained networks on large-scale image datasets or alternative data-rich sources (i.e. bacterial and viral pneumonia radiographs). The experimental results indicate that the TL approach outperforms the performance obtained without TL, for the COVID-19 classification task in chest X-ray images.

scholarly journals Improving Semi-Supervised Learning for Audio Classification with FixMatch

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1807
Author(s):  
Sascha Grollmisch ◽  
Estefanía Cano
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Transfer Learning ◽  
Data Transfer ◽  
State Of The Art ◽  
Training Data ◽  
Audio Classification ◽  
Image Domain ◽  
Full Dataset ◽  
Audio Data

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly rely on the augmentation of unannotated data. This is vastly unexplored for audio data. In this work, SSL using the state-of-the-art FixMatch approach is evaluated on three audio classification tasks, including music, industrial sounds, and acoustic scenes. The performance of FixMatch is compared to Convolutional Neural Networks (CNN) trained from scratch, Transfer Learning, and SSL using the Mean Teacher approach. Additionally, a simple yet effective approach for selecting suitable augmentation methods for FixMatch is introduced. FixMatch with the proposed modifications always outperformed Mean Teacher and the CNNs trained from scratch. For the industrial sounds and music datasets, the CNN baseline performance using the full dataset was reached with less than 5% of the initial training data, demonstrating the potential of recent SSL methods for audio data. Transfer Learning outperformed FixMatch only for the most challenging dataset from acoustic scene classification, showing that there is still room for improvement.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

scholarly journals ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

2021 ◽  
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
State Of The Art ◽  
Image Decomposition ◽  
Natural Environments ◽  
Decomposition Algorithms ◽  
Ambient Light ◽  
Fine Grained ◽  
Large Scale Dataset ◽  
Direct Illumination

AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.

scholarly journals BeautyNet: Joint Multiscale CNN and Transfer Learning Method for Unconstrained Facial Beauty Prediction

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Yikui Zhai ◽  
He Cao ◽  
Wenbo Deng ◽  
Junying Gan ◽  
Vincenzo Piuri ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Classification Accuracy ◽  
Learning Strategy ◽  
State Of The Art ◽  
Activation Function ◽  
Training Data ◽  
Fine Grained ◽  
Pattern Recognition Problem ◽  
Face Features ◽  
Facial Beauty

Because of the lack of discriminative face representations and scarcity of labeled training data, facial beauty prediction (FBP), which aims at assessing facial attractiveness automatically, has become a challenging pattern recognition problem. Inspired by recent promising work on fine-grained image classification using the multiscale architecture to extend the diversity of deep features, BeautyNet for unconstrained facial beauty prediction is proposed in this paper. Firstly, a multiscale network is adopted to improve the discriminative of face features. Secondly, to alleviate the computational burden of the multiscale architecture, MFM (max-feature-map) is utilized as an activation function which can not only lighten the network and speed network convergence but also benefit the performance. Finally, transfer learning strategy is introduced here to mitigate the overfitting phenomenon which is caused by the scarcity of labeled facial beauty samples and improves the proposed BeautyNet’s performance. Extensive experiments performed on LSFBD demonstrate that the proposed scheme outperforms the state-of-the-art methods, which can achieve 67.48% classification accuracy.

Efficient Vector Partitioning Algorithms for Graph Clustering

2020 ◽  
Vol 1 (2) ◽  
pp. 101-123
Author(s):  
Hiroaki Shiokawa ◽  
Yasunori Futamura
Keyword(s):  
Social Networks ◽  
Large Scale ◽  
Clustering Algorithm ◽  
Ground Truth ◽  
Graph Clustering ◽  
Mining Communities ◽  
Fine Grained ◽  
Efficient Vector ◽  
Public Datasets ◽  
Many Core

This paper addressed the problem of finding clusters included in graph-structured data such as Web graphs, social networks, and others. Graph clustering is one of the fundamental techniques for understanding structures present in the complex graphs such as Web pages, social networks, and others. In the Web and data mining communities, the modularity-based graph clustering algorithm is successfully used in many applications. However, it is difficult for the modularity-based methods to find fine-grained clusters hidden in large-scale graphs; the methods fail to reproduce the ground truth. In this paper, we present a novel modularity-based algorithm, \textit{CAV}, that shows better clustering results than the traditional algorithm. The proposed algorithm employs a cohesiveness-aware vector partitioning into the graph spectral analysis to improve the clustering accuracy. Additionally, this paper also presents a novel efficient algorithm \textit{P-CAV} for further improving the clustering speed of CAV; P-CAV is an extension of CAV that utilizes the thread-based parallelization on a many-core CPU. Our extensive experiments on synthetic and public datasets demonstrate the performance superiority of our approaches over the state-of-the-art approaches.

Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

2021 ◽  
pp. 2050012
Author(s):  
Peilian Zhao ◽  
Cunli Mao ◽  
Zhengtao Yu
Keyword(s):  
Sentiment Analysis ◽  
Domain Knowledge ◽  
Opinion Mining ◽  
Data Augmentation ◽  
Training Data ◽  
Knowledge Graph ◽  
Fine Grained ◽  
Learning Framework ◽  
Proposed Model ◽  
Real World Applications

Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.

scholarly journals Large-scale, high-resolution comparison of the core visual object recognition behavior of humans, monkeys, and state-of-the-art deep artificial neural networks

2018 ◽  
Author(s):  
Rishi Rajalingham ◽  
Elias B. Issa ◽  
Pouya Bashivan ◽  
Kohitij Kar ◽  
Kailyn Schmidt ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
High Resolution ◽  
Large Scale ◽  
State Of The Art ◽  
Neural Mechanisms ◽  
Mechanistic Models ◽  
Object Discrimination ◽  
Ann Models ◽  
Artificial Neural

ABSTRACTPrimates—including humans—can typically recognize objects in visual images at a glance even in the face of naturally occurring identity-preserving image transformations (e.g. changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechanistic models that quantitatively explain this behavior by predicting primate performance for each and every image. Here, we applied this stringent behavioral prediction test to the leading mechanistic models of primate vision (specifically, deep, convolutional, artificial neural networks; ANNs) by directly comparing their behavioral signatures against those of humans and rhesus macaque monkeys. Using high-throughput data collection systems for human and monkey psychophysics, we collected over one million behavioral trials for 2400 images over 276 binary object discrimination tasks. Consistent with previous work, we observed that state-of-the-art deep, feed-forward convolutional ANNs trained for visual categorization (termed DCNNIC models) accurately predicted primate patterns of object-level confusion. However, when we examined behavioral performance for individual images within each object discrimination task, we found that all tested DCNNIC models were significantly non-predictive of primate performance, and that this prediction failure was not accounted for by simple image attributes, nor rescued by simple model modifications. These results show that current DCNNIC models cannot account for the image-level behavioral patterns of primates, and that new ANN models are needed to more precisely capture the neural mechanisms underlying primate object vision. To this end, large-scale, high-resolution primate behavioral benchmarks—such as those obtained here—could serve as direct guides for discovering such models.SIGNIFICANCE STATEMENTRecently, specific feed-forward deep convolutional artificial neural networks (ANNs) models have dramatically advanced our quantitative understanding of the neural mechanisms underlying primate core object recognition. In this work, we tested the limits of those ANNs by systematically comparing the behavioral responses of these models with the behavioral responses of humans and monkeys, at the resolution of individual images. Using these high-resolution metrics, we found that all tested ANN models significantly diverged from primate behavior. Going forward, these high-resolution, large-scale primate behavioral benchmarks could serve as direct guides for discovering better ANN models of the primate visual system.

scholarly journals Attending to Entities for Better Text Understanding

2020 ◽  
Vol 34 (05) ◽  
pp. 7554-7561
Author(s):  
Pengxiang Cheng ◽  
Katrin Erk
Keyword(s):  
Large Scale ◽  
Human Performance ◽  
State Of The Art ◽  
Syntactic Structure ◽  
Semantic Knowledge ◽  
Training Data ◽  
Language Models ◽  
Long Distance ◽  
Future Directions ◽  
Text Understanding

Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art results, approaching human performance. This clearly demonstrates the power of the stacked self-attention architecture when paired with a sufficient number of layers and a large amount of pre-training data. However, on tasks that require complex and long-distance reasoning where surface-level cues are not enough, there is still a large gap between the pre-trained models and human performance. Strubell et al. (2018) recently showed that it is possible to inject knowledge of syntactic structure into a model through supervised self-attention. We conjecture that a similar injection of semantic knowledge, in particular, coreference information, into an existing model would improve performance on such complex problems. On the LAMBADA (Paperno et al. 2016) task, we show that a model trained from scratch with coreference as auxiliary supervision for self-attention outperforms the largest GPT-2 model, setting the new state-of-the-art, while only containing a tiny fraction of parameters compared to GPT-2. We also conduct a thorough analysis of different variants of model architectures and supervision configurations, suggesting future directions on applying similar techniques to other problems.

Sign in / Sign up

Export Citation Format

Share Document