Acute lymphocytic leukemia (ALL) is a deadly cancer that not only affects adults but also accounts for about 25% of childhood cancers. Timely and accurate diagnosis of the cancer is an important premise for effective treatment to improve survival rate. Since the image of leukemic B-lymphoblast cells (cancer cells) under the microscope is very similar in morphology to that of normal B-lymphoid precursors (normal cells), it is difficult to distinguish between cancer cells and normal cells. Therefore, we propose the ViT-CNN ensemble model to classify cancer cells images and normal cells images to assist in the diagnosis of acute lymphoblastic leukemia. The ViT-CNN ensemble model is an ensemble model that combines the vision transformer model and convolutional neural network (CNN) model. The vision transformer model is an image classification model based entirely on the transformer structure, which has completely different feature extraction method from the CNN model. The ViT-CNN ensemble model can extract the features of cells images in two completely different ways to achieve better classification results. In addition, the data set used in this article is an unbalanced data set and has a certain amount of noise, and we propose a difference enhancement-random sampling (DERS) data enhancement method, create a new balanced data set, and use the symmetric cross-entropy loss function to reduce the impact of noise in the data set. The classification accuracy of the ViT-CNN ensemble model on the test set has reached 99.03%, and it is proved through experimental comparison that the effect is better than other models. The proposed method can accurately distinguish between cancer cells and normal cells and can be used as an effective method for computer-aided diagnosis of acute lymphoblastic leukemia.

/pdf/method-for-diagnosis-of-acute-lymphoblastic-leukemia-based-1ciqsky55j.pdf

Method for Diagnosis of Acute Lymphoblastic Leukemia Based on ViT-CNN Ensemble Model.

Accurate and timely landslide susceptibility mapping (LSM) is essential to effectively reduce the risk of landslide. In recent years, deep learning has been successfully applied to landslide susceptibility assessment due to the strong ability of fitting. However, in actual applications, the number of labeled samples is usually not sufficient for the training component. In this paper, a deep neural network model based on semi-supervised learning (SSL-DNN) for landslide susceptibility is proposed, which makes full use of a large number of spatial information (unlabeled data) with limited labeled data in the region to train the mode. Taking Jiaohe County in Jilin Province, China as an example, the landslide inventory from 2000 to 2017 was collected and 12 metrological, geographical, and human explanatory factors were compiled. Meanwhile, supervised models such as deep neural network (DNN), support vector machine (SVM), and logistic regression (LR) were implemented for comparison. Then, the landslide susceptibility was plotted and a series of evaluation tools such as class accuracy, predictive rate curves (AUC), and information gain ratio (IGR) were calculated to compare the prediction of models and factors. Experimental results indicate that the proposed SSL-DNN model (AUC = 0.898) outperformed all the comparison models. Therefore, semi-supervised deep learning could be considered as a potential approach for LSM.

Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China

Traffic sign recognition is a classification problem that poses challenges for computer vision and machine learning algorithms. Although both computer vision and machine learning techniques have constantly been improved to solve this problem, the sudden rise in the number of unlabeled traffic signs has become even more challenging. Large data collation and labeling are tedious and expensive tasks that demand much time, expert knowledge, and fiscal resources to satisfy the hunger of deep neural networks. Aside from that, the problem of having unbalanced data also poses a greater challenge to computer vision and machine learning algorithms to achieve better performance. These problems raise the need to develop algorithms that can fully exploit a large amount of unlabeled data, use a small amount of labeled samples, and be robust to data imbalance to build an efficient and high-quality classifier. In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data. The framework integrates weakly-supervised learning and self-training with self-paced learning to generate attention maps to augment the training set and utilizes a novel pseudo-label generation and selection algorithm to generate and select pseudo-labeled samples. The method improves the performance by: (1) normalizing the class-wise confidence levels to prevent the model from ignoring hard-to-learn samples, thereby solving the imbalanced data problem; (2) jointly learning a model and optimizing pseudo-labels generated on unlabeled data; and (3) enlarging the training set to satisfy the hunger of deep learning models. Extensive evaluations on two public traffic sign recognition datasets demonstrate the effectiveness of the proposed technique and provide a potential solution for practical applications.

https://www.mdpi.com/1424-8220/20/9/2684/pdf

Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning

Automatic detection and recognition of traffic signs have many applications. However, some problems can affect the accuracy of the existing algorithms, such as changes in environmental light conditions, shadows, the presence of objects of the same colour, significant changes in scale and rotation, as well as obstacles in front of the traffic signs. To overcome these difficulties, a reference image database is usually used that includes different modes of appearing the traffic signs in the images. In order to overcome the effects of scale and rotation, in this paper a new method is presented in which only one reference image is needed for each sign to recognise the traffic sign in an image. In the proposed method, imaging is done in stereo. Using the captured image pair, a virtual image is generated which is then used to recognise the sign. As a result, the recognition is carried out with a minimum number of reference images. Experiments show that the proposed algorithm significantly improves recognition results. The traffic signs are recognised with 93.1% accuracy that enjoys a 4.9% improvement over traditional methods.

Improving traffic sign recognition results in urban areas by overcoming the impact of scale and rotation

Semi-supervised point cloud segmentation using self-training with label confidence prediction

Semi-supervised learning is a machine learning approach that tackles the challenge of having a large set of unlabeled data and few labeled ones. In this paper we adopt a semi-supervised self-training method to increase the amount of training data, prevent overfitting and improve the performance of deep models by proposing a novel selection algorithm that prevents mistake reinforcement which is a common thing in conventional self-training models. The model leverages, unlabeled data and specifically, after each training, we first generate pseudo-labels on the unlabeled set to be added to the labeled training samples. Next, we select the top-k most-confident pseudo-labeled images from each unlabeled class with their pseudo-labels and update the training data, and retrain the network on the updated training data. The method improves the accuracy in two-fold; bridging the gap in the appearance of visual objects, and enlarging the training set to meet the demands of deep models. We demonstrated the effectiveness of the model by conducting experiments on four state-of-the-art fine-grained datasets, which include Stanford Dogs, Stanford Cars, 102-Oxford flowers, and CUB-200-2011. We further evaluated the model on some coarse-grain data. Experimental results clearly show that our proposed framework has better performance than some previous works on the same data; the model obtained higher classification accuracy than most of the supervised learning models.

/pdf/semi-supervised-learning-for-fine-grained-classification-46k4ky63f0.pdf

Semi-Supervised Learning for Fine-Grained Classification With Self-Training

The unavailability of large amounts of well-labeled data poses a significant challenge in many medical imaging tasks. Even in the likelihood of having access to sufficient data, the process of accurately labeling the data is an arduous and time-consuming one, requiring expertise skills. Again, the issue of unbalanced data further compounds the abovementioned problems and presents a considerable challenge for many machine learning algorithms. In lieu of this, the ability to develop algorithms that can exploit large amounts of unlabeled data together with a small amount of labeled data, while demonstrating robustness to data imbalance, can offer promising prospects in building highly efficient classifiers. This work proposes a semisupervised learning method that integrates self-training and self-paced learning to generate and select pseudolabeled samples for classifying breast cancer histopathological images. A novel pseudolabel generation and selection algorithm is introduced in the learning scheme to generate and select highly confident pseudolabeled samples from both well-represented classes to less-represented classes. Such a learning approach improves the performance by jointly learning a model and optimizing the generation of pseudolabels on unlabeled-target data to augment the training data and retraining the model with the generated labels. A class balancing framework that normalizes the class-wise confidence scores is also proposed to prevent the model from ignoring samples from less represented classes (hard-to-learn samples), hence effectively handling the issue of data imbalance. Extensive experimental evaluation of the proposed method on the BreakHis dataset demonstrates the effectiveness of the proposed method.

/pdf/a-semisupervised-learning-scheme-with-self-paced-learning-504gckjzzr.pdf

A Semisupervised Learning Scheme with Self-Paced Learning for Classifying Breast Cancer Histopathological Images

Automatically classifying skin lesion is a challenging task owing to reasons such as high intra class variations, similarities between inter-class images, occlusions in dermoscopy images that impede accurate lesion localization, not to mention data unavailability Considering that unlabeled data is abundant and cheap, this work proposes a classification framework that integrates the semi-supervised learning concepts of self-training and self-paced learning to classifying skin lesions First, accurate instance segmentation is performed using the Mask R-CNN model to effectively localize and preserve the appearance and size of the skin lesions in an image Then, a semi-supervised self-training scheme that utilizes self-paced learning strategy is implemented to generate and select pseudo-labeled samples to augment the training data The proposed framework ensures that; 1) the spatial locations of skin lesions are accurately localized and preserved, which is critical for extracting semantically meaningful information akin to classification; 2) sufficient data samples are generated to enlarge the training data to avoid overfitting; 3) a model learns both “easy” and “hard” samples during training without necessarily ignoring features from less represented classes Extensive experiments are performed using the ISIC dataset and results obtained demonstrate the effectiveness of the proposed approach

Learning to Classify Skin Lesions via Self-Training and Self-Paced Learning

This study proposes a self-paced learning scheme that integrates self-training and deep learning to select and learn labeled and unlabeled data samples for classifying anterior-posterior chest images as either being pneumonia-infected or normal. With this new approach, a model is first trained with labeled data. The model is evaluated on unlabeled data to generate pseudo labels for the unlabeled data. Using a novel selection scheme, the pseudo-labeled samples are then selected to update the model in next training iteration of the semi-supervised training process. The selected pseudo-labeled images to be added to the next training iteration are images with the most confident probabilities from every unlabeled class. Such a selection scheme prevents mistake reinforcement, which is a prevalent occurrence in self-training. With deep models having the tendency to latch onto well-represented class samples while ignoring less transferable and represented classes, especially in the case of unbalanced data, the proposed method utilizes a novel algorithm for the generation and selection of reliable top-K pseudo-labeled samples to be used in updating the model during the next training phase. Such an approach does not only force the model to learn the hard samples in the training data, it also helps enlarge the training set by generating enough samples that satisfy the hunger of deep models. Extensive experimental evaluation of the proposed method yields higher accuracy results compared to methods mentioned in the literature on the same dataset, an indication of the effectiveness of the proposed method.

/pdf/a-robust-pneumonia-classification-approach-based-on-self-3hv4g3p6fa.pdf

Sarpong Kwadwo Asare

Papers

Semi-Supervised Learning for Fine-Grained Classification With Self-Training

Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning

A Semisupervised Learning Scheme with Self-Paced Learning for Classifying Breast Cancer Histopathological Images

Learning to Classify Skin Lesions via Self-Training and Self-Paced Learning

A Robust Pneumonia Classification Approach based on Self-Paced Learning