PyTorchKR Papers

최신 논문

총 11,126편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.07148

Data Augmentation and CNN Classification For Automatic COVID-19 Diagnosis From CT-Scan Images On Small Dataset

We present an automatic COVID1-19 diagnosis framework from lung CT images. The focus is on signal processing and classification on small datasets with efforts putting into exploring data preparation and augmentation to improve the generalization capability of the 2D CNN classification models. We propose a unique and effective data augmentation method using multiple Hounsfield Unit (HU) normalization windows. In addition, the original slice image is cropped to exclude background, and a filter is applied to filter out closed-lung images. For the classification network, we choose to use 2D Densenet and Xception with the feature pyramid network (FPN). To further improve the classification accuracy, an ensemble of multiple CNN models and HU windows is used. On the training/validation dataset, we achieve a patient classification accuracy of 93.39%.

arXiv:2108.07049공식 코드 · Papers with Code

Towards Efficient and Data Agnostic Image Classification Training Pipeline for Embedded Systems

Nowadays deep learning-based methods have achieved a remarkable progress at the image classification task among a wide range of commonly used datasets (ImageNet, CIFAR, SVHN, Caltech 101, SUN397, etc.). SOTA performance on each of the mentioned datasets is obtained by careful tuning of the model architecture and training tricks according to the properties of the target data. Although this approach allows setting academic records, it is unrealistic that an average data scientist would have enough resources to build a sophisticated training pipeline for every image classification task he meets in practice. This work is focusing on reviewing the latest augmentation and regularization methods for the image classification and exploring ways to automatically choose some of the most important hyperparameters: total number of epochs, initial learning rate value and it's schedule. Having a training procedure equipped with a lightweight modern CNN architecture (like bileNetV3 or EfficientNet), sufficient level of regularization and adaptive to data learning rate schedule, we can achieve a reasonable performance on a variety of downstream image classification tasks without manual tuning of parameters to each particular task. Resulting models are computationally efficient and can be deployed to CPU using the OpenVINO toolkit. Source code is available as a part of the OpenVINO Training Extensions (https://github.com/openvinotoolkit/training_extensions).

arXiv:2108.06730

Towards Visual Explainable Active Learning for Zero-Shot Classification

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a class-attribute matrix to define which classes have which attributes. Designing a suitable class-attribute matrix is the key to the subsequent procedure, but this design process is tedious and trial-and-error with no guidance. This paper proposes a visual explainable active learning approach with its design and implementation called semantic navigator to solve the above problems. This approach promotes human-AI teaming with four actions (ask, explain, recommend, respond) in each interaction loop. The machine asks contrastive questions to guide humans in the thinking process of attributes. A novel visualization called semantic map explains the current status of the machine. Therefore analysts can better understand why the machine misclassifies objects. Moreover, the machine recommends the labels of classes for each attribute to ease the labeling burden. Finally, humans can steer the model by modifying the labels interactively, and the machine adjusts its recommendations. The visual explainable active learning approach improves humans' efficiency of building zero-shot classification models interactively, compared with the method without guidance. We justify our results with user studies using the standard benchmarks for zero-shot classification.

arXiv:2108.06274

Towards artificially intelligent recycling Improving image processing for waste classification

The ever-increasing amount of global refuse is overwhelming the waste and recycling management industries. The need for smart systems for environmental monitoring and the enhancement of recycling processes is thus greater than ever. Amongst these efforts lies IBM's Wastenet project which aims to improve recycling by using artificial intelligence for waste classification. The work reported in this paper builds on this project through the use of transfer learning and data augmentation techniques to ameliorate classification accuracy. Starting with a convolutional neural network (CNN), a systematic approach is followed for selecting appropriate splitting ratios and for tuning multiple training parameters including learning rate schedulers, layers freezing, batch sizes and loss functions, in the context of the given scenario which requires classification of waste into different recycling types. Results are compared and contrasted using 10-fold cross validation and demonstrate that the model developed achieves a 91.21% test accuracy. Subsequently, a range of data augmentation techniques are then incorporated into this work including flipping, rotation, shearing, zooming, and brightness control. Results show that these augmentation techniques further improve the test accuracy of the final model to 95.40%. Unlike other work reported in the field, this paper provides full details regarding the training of the model. Furthermore, the code for this work has been made open-source and we have demonstrated that the model can perform successful real-time classification of recycling waste items using a standard computer webcam.

arXiv:2108.06230공식 코드 · Papers with Code

Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds

While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classification. We present the first generative approach for both ZSL and Generalized ZSL (GZSL) on 3D data, that can handle both classification and, for the first time, semantic segmentation. We show that it reaches or outperforms the state of the art on ModelNet40 classification for both inductive ZSL and inductive GZSL. For semantic segmentation, we created three benchmarks for evaluating this new ZSL task, using S3DIS, ScanNet and SemanticKITTI. Our experiments show that our method outperforms strong baselines, which we additionally propose for this task.

arXiv:2108.06207

Disentangling Hate in Online Memes

Hateful and offensive content detection has been extensively explored in a single modality such as text. However, such toxic information could also be communicated via multimodal content such as online memes. Therefore, detecting multimodal hateful content has recently garnered much attention in academic and industry research communities. This paper aims to contribute to this emerging research topic by proposing DisMultiHate, which is a novel framework that performed the classification of multimodal hateful content. Specifically, DisMultiHate is designed to disentangle target entities in multimodal memes to improve hateful content classification and explainability. We conduct extensive experiments on two publicly available hateful and offensive memes datasets. Our experiment results show that DisMultiHate is able to outperform state-of-the-art unimodal and multimodal baselines in the hateful meme classification task. Empirical case studies were also conducted to demonstrate DisMultiHate's ability to disentangle target entities in memes and ultimately showcase DisMultiHate's explainability of the multimodal hateful content classification task.

arXiv:2108.05947공식 코드 · Papers with Code

Room Classification on Floor Plan Graphs using Graph Neural Networks

We present our approach to improve room classification task on floor plan maps of buildings by representing floor plans as undirected graphs and leveraging graph neural networks to predict the room categories. Rooms in the floor plans are represented as nodes in the graph with edges representing their adjacency in the map. We experiment with House-GAN dataset that consists of floor plan maps in vector format and train multilayer perceptron and graph neural networks. Our results show that graph neural networks, specifically GraphSAGE and Topology Adaptive GCN were able to achieve accuracy of 80% and 81% respectively outperforming baseline multilayer perceptron by more than 15% margin.

arXiv:2108.05927

Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages

With the growth of social media, the spread of hate speech is also increasing rapidly. Social media are widely used in many countries. Also Hate Speech is spreading in these countries. This brings a need for multilingual Hate Speech detection algorithms. Much research in this area is dedicated to English at the moment. The HASOC track intends to provide a platform to develop and optimize Hate Speech detection algorithms for Hindi, German and English. The dataset is collected from a Twitter archive and pre-classified by a machine learning system. HASOC has two sub-task for all three languages: task A is a binary classification problem (Hate and Not Offensive) while task B is a fine-grained classification problem for three classes (HATE) Hate speech, OFFENSIVE and PROFANITY. Overall, 252 runs were submitted by 40 teams. The performance of the best classification algorithms for task A are F1 measures of 0.51, 0.53 and 0.52 for English, Hindi, and German, respectively. For task B, the best classification algorithms achieved F1 measures of 0.26, 0.33 and 0.29 for English, Hindi, and German, respectively. This article presents the tasks and the data development as well as the results. The best performing algorithms were mainly variants of the transformer architecture BERT. However, also other systems were applied with good success

arXiv:2108.06128공식 코드 · Papers with Code

Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices

Deep learning has celebrated resounding successes in many application areas of relevance to the Internet of Things (IoT), such as computer vision and machine listening. These technologies must ultimately be brought directly to the edge to fully harness the power of deep learning for the IoT. The obvious challenge is that deep learning techniques can only be implemented on strictly resource-constrained edge devices if the models are radically downsized. This task relies on different model compression techniques, such as network pruning, quantization, and the recent advancement of XNOR-Net. This study examines the suitability of these techniques for audio classification on microcontrollers. We present an application of XNOR-Net for end-to-end raw audio classification and a comprehensive empirical study comparing this approach with pruning-and-quantization methods. We show that raw audio classification with XNOR yields comparable performance to regular full precision networks for small numbers of classes while reducing memory requirements 32-fold and computation requirements 58-fold. However, as the number of classes increases significantly, performance degrades, and pruning-and-quantization based compression techniques take over as the preferred technique being able to satisfy the same space constraints but requiring approximately 8x more computation. We show that these insights are consistent between raw audio classification and image classification using standard benchmark sets. To the best of our knowledge, this is the first study to apply XNOR to end-to-end audio classification and evaluate it in the context of alternative techniques. All codes are publicly available on GitHub.

arXiv:2108.05697

Local Correlation Clustering with Asymmetric Classification Errors

In the Correlation Clustering problem, we are given a complete weighted graph $G$ with its edges labeled as "similar" and "dissimilar" by a noisy binary classifier. For a clustering $\mathcal{C}$ of graph $G$, a similar edge is in disagreement with $\mathcal{C}$, if its endpoints belong to distinct clusters; and a dissimilar edge is in disagreement with $\mathcal{C}$ if its endpoints belong to the same cluster. The disagreements vector, $\text{dis}$, is a vector indexed by the vertices of $G$ such that the $v$-th coordinate $\text{dis}_v$ equals the weight of all disagreeing edges incident on $v$. The goal is to produce a clustering that minimizes the $\ell_p$ norm of the disagreements vector for $p\geq 1$. We study the $\ell_p$ objective in Correlation Clustering under the following assumption: Every similar edge has weight in the range of $[\alpha\mathbf{w},\mathbf{w}]$ and every dissimilar edge has weight at least $\alpha\mathbf{w}$ (where $\alpha \leq 1$ and $\mathbf{w}>0$ is a scaling parameter). We give an $O\left((\frac{1}{\alpha})^{\frac{1}{2}-\frac{1}{2p}}\cdot \log\frac{1}{\alpha}\right)$ approximation algorithm for this problem. Furthermore, we show an almost matching convex programming integrality gap.

arXiv:2108.05696

Correlation Clustering with Asymmetric Classification Errors

In the Correlation Clustering problem, we are given a weighted graph $G$ with its edges labeled as "similar" or "dissimilar" by a binary classifier. The goal is to produce a clustering that minimizes the weight of "disagreements": the sum of the weights of "similar" edges across clusters and "dissimilar" edges within clusters. We study the correlation clustering problem under the following assumption: Every "similar" edge $e$ has weight $\mathbf{w}_e\in[\alpha \mathbf{w}, \mathbf{w}]$ and every "dissimilar" edge $e$ has weight $\mathbf{w}_e\geq \alpha \mathbf{w}$ (where $\alpha\leq 1$ and $\mathbf{w}>0$ is a scaling parameter). We give a $(3 + 2 \log_e (1/\alpha))$ approximation algorithm for this problem. This assumption captures well the scenario when classification errors are asymmetric. Additionally, we show an asymptotically matching Linear Programming integrality gap of $\Omega(\log 1/\alpha)$.

arXiv:2108.05595

Reinforcement Learning Approach to Active Learning for Image Classification

Machine Learning requires large amounts of labeled data to fit a model. Many datasets are already publicly available, nevertheless forcing application possibilities of machine learning to the domains of those public datasets. The ever-growing penetration of machine learning algorithms in new application areas requires solutions for the need for data in those new domains. This thesis works on active learning as one possible solution to reduce the amount of data that needs to be processed by hand, by processing only those datapoints that specifically benefit the training of a strong model for the task. A newly proposed framework for framing the active learning workflow as a reinforcement learning problem is adapted for image classification and a series of three experiments is conducted. Each experiment is evaluated and potential issues with the approach are outlined. Each following experiment then proposes improvements to the framework and evaluates their impact. After the last experiment, a final conclusion is drawn, unfortunately rejecting this work's hypothesis and outlining that the proposed framework at the moment is not capable of improving active learning for image classification with a trained reinforcement learning agent.

arXiv:2108.05761

Analyzing hierarchical multi-view MRI data with StaPLR: An application to Alzheimer's disease classification

Multi-view data refers to a setting where features are divided into feature sets, for example because they correspond to different sources. Stacked penalized logistic regression (StaPLR) is a recently introduced method that can be used for classification and automatically selecting the views that are most important for prediction. We introduce an extension of this method to a setting where the data has a hierarchical multi-view structure. We also introduce a new view importance measure for StaPLR, which allows us to compare the importance of views at any level of the hierarchy. We apply our extended StaPLR algorithm to Alzheimer's disease classification where different MRI measures have been calculated from three scan types: structural MRI, diffusion-weighted MRI, and resting-state fMRI. StaPLR can identify which scan types and which derived MRI measures are most important for classification, and it outperforms elastic net regression in classification performance.

arXiv:2108.05305

ConvNets vs. Transformers: Whose Visual Representations are More Transferable?

Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet classification, it is still unclear whether the learned representations are as transferable as or even more transferable than ConvNets' features. To address this point, we systematically investigate the transfer learning ability of ConvNets and vision transformers in 15 single-task and multi-task performance evaluations. Given the strong correlation between the performance of pre-trained models and transfer learning, we include 2 residual ConvNets (i.e., R-101x3 and R-152x4) and 3 Transformer-based visual backbones (i.e., ViT-B, ViT-L and Swin-B), which have close error rates on ImageNet, that indicate similar transfer learning performance on downstream datasets. We observe consistent advantages of Transformer-based backbones on 13 downstream tasks (out of 15), including but not limited to fine-grained classification, scene recognition (classification, segmentation and depth estimation), open-domain classification, face recognition, etc. More specifically, we find that two ViT models heavily rely on whole network fine-tuning to achieve performance gains while Swin Transformer does not have such a requirement. Moreover, vision transformers behave more robustly in multi-task learning, i.e., bringing more improvements when managing mutually beneficial tasks and reducing performance losses when tackling irrelevant tasks. We hope our discoveries can facilitate the exploration and exploitation of vision transformers in the future.

arXiv:2108.05258공식 코드 · Papers with Code

Deep Learning Classification of Lake Zooplankton

Plankton are effective indicators of environmental change and ecosystem health in freshwater habitats, but collection of plankton data using manual microscopic methods is extremely labor-intensive and expensive. Automated plankton imaging offers a promising way forward to monitor plankton communities with high frequency and accuracy in real-time. Yet, manual annotation of millions of images proposes a serious challenge to taxonomists. Deep learning classifiers have been successfully applied in various fields and provided encouraging results when used to categorize marine plankton images. Here, we present a set of deep learning models developed for the identification of lake plankton, and study several strategies to obtain optimal performances,which lead to operational prescriptions for users. To this aim, we annotated into 35 classes over 17900 images of zooplankton and large phytoplankton colonies, detected in Lake Greifensee (Switzerland) with the Dual Scripps Plankton Camera. Our best models were based on transfer learning and ensembling, which classified plankton images with 98% accuracy and 93% F1 score. When tested on freely available plankton datasets produced by other automated imaging tools (ZooScan, FlowCytobot and ISIIS), our models performed better than previously used models. Our annotated data, code and classification models are freely available online.

arXiv:2108.05077공식 코드 · Papers with Code

Mining the Benefits of Two-stage and One-stage HOI Detection

Two-stage methods have dominated Human-Object Interaction (HOI) detection for several years. Recently, one-stage HOI detection methods have become popular. In this paper, we aim to explore the essential pros and cons of two-stage and one-stage methods. With this as the goal, we find that conventional two-stage methods mainly suffer from positioning positive interactive human-object pairs, while one-stage methods are challenging to make an appropriate trade-off on multi-task learning, i.e., object detection, and interaction classification. Therefore, a core problem is how to take the essence and discard the dregs from the conventional two types of methods. To this end, we propose a novel one-stage framework with disentangling human-object detection and interaction classification in a cascade manner. In detail, we first design a human-object pair generator based on a state-of-the-art one-stage HOI detector by removing the interaction classification module or head and then design a relatively isolated interaction classifier to classify each human-object pair. Two cascade decoders in our proposed framework can focus on one specific task, detection or interaction classification. In terms of the specific implementation, we adopt a transformer-based HOI detector as our base model. The newly introduced disentangling paradigm outperforms existing methods by a large margin, with a significant relative mAP gain of 9.32% on HICO-Det. The source codes are available at https://github.com/YueLiao/CDN.

arXiv:2108.04815

The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data

Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss function in such tasks, a growing number of approaches have turned to a family of contrastive learning-based losses. Even though performance metrics such as accuracy, sensitivity and specificity are regularly used for the evaluation of CNN classifiers, the features that these classifiers actually learn are rarely identified and their effect on the classification performance on out-of-distribution test samples is insufficiently explored. In this paper, motivated by the real-world task of lung nodule classification, we investigate the features that a CNN learns when trained and tested on different distributions of a synthetic dataset with controlled modes of variation. We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.

arXiv:2108.04663

Deep Learning for Breast Cancer Classification: Enhanced Tangent Function

Background and Aim: Recently, deep learning using convolutional neural network has been used successfully to classify the images of breast cells accurately. However, the accuracy of manual classification of those histopathological images is comparatively low. This research aims to increase the accuracy of the classification of breast cancer images by utilizing a Patch-Based Classifier (PBC) along with deep learning architecture. Methodology: The proposed system consists of a Deep Convolutional Neural Network (DCNN) that helps in enhancing and increasing the accuracy of the classification process. This is done by the use of the Patch-based Classifier (PBC). CNN has completely different layers where images are first fed through convolutional layers using hyperbolic tangent function together with the max-pooling layer, drop out layers, and SoftMax function for classification. Further, the output obtained is fed to a patch-based classifier that consists of patch-wise classification output followed by majority voting. Results: The results are obtained throughout the classification stage for breast cancer images that are collected from breast-histology datasets. The proposed solution improves the accuracy of classification whether or not the images had normal, benign, in-situ, or invasive carcinoma from 87% to 94% with a decrease in processing time from 0.45 s to 0.2s on average. Conclusion: The proposed solution focused on increasing the accuracy of classifying cancer in the breast by enhancing the image contrast and reducing the vanishing gradient. Finally, this solution for the implementation of the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique and modified tangent function helps in increasing the accuracy.

arXiv:2108.04614

White blood cell subtype detection and classification

Machine learning has endless applications in the health care industry. White blood cell classification is one of the interesting and promising area of research. The classification of the white blood cells plays an important part in the medical diagnosis. In practise white blood cell classification is performed by the haematologist by taking a small smear of blood and careful examination under the microscope. The current procedures to identify the white blood cell subtype is more time taking and error-prone. The computer aided detection and diagnosis of the white blood cells tend to avoid the human error and reduce the time taken to classify the white blood cells. In the recent years several deep learning approaches have been developed in the context of classification of the white blood cells that are able to identify but are unable to localize the positions of white blood cells in the blood cell image. Following this, the present research proposes to utilize YOLOv3 object detection technique to localize and classify the white blood cells with bounding boxes. With exhaustive experimental analysis, the proposed work is found to detect the white blood cell with 99.2% accuracy and classify with 90% accuracy.

arXiv:2108.04595

Label-informed Graph Structure Learning for Node Classification

Graph Neural Networks (GNNs) have achieved great success among various domains. Nevertheless, most GNN methods are sensitive to the quality of graph structures. To tackle this problem, some studies exploit different graph structure learning strategies to refine the original graph structure. However, these methods only consider feature information while ignoring available label information. In this paper, we propose a novel label-informed graph structure learning framework which incorporates label information explicitly through a class transition matrix. We conduct extensive experiments on seven node classification benchmark datasets and the results show that our method outperforms or matches the state-of-the-art baselines.