Related papers: Image Classification with Small Datasets: Overview…

Because hyperspectral remote sensing images contain a lot of redundant information and the data structure is highly non-linear, leading to low classification accuracy of traditional machine learning methods. The latest research shows that…

Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates. We propose a resource-efficient data-cleaning protocol to identify issues that escaped previous curation. The…

This paper presents a comprehensive evaluation framework for image segmentation algorithms, encompassing naive methods, machine learning approaches, and deep learning techniques. We begin by introducing the fundamental concepts and…

Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited annotated data, high intra-class variability, and subtle inter-class differences often…

In many application domains such as medicine, information retrieval, cybersecurity, social media, etc., datasets used for inducing classification models often have an unequal distribution of the instances of each class. This situation,…

Ocular biometric systems working in unconstrained environments usually face the problem of small within-class compactness caused by the multiple factors that jointly degrade the quality of the obtained data. In this work, we propose an…

Benchmarking involves designing scientific test methods, tools, and frameworks to quantitatively and comparably assess specific performance indicators of certain test subjects. With the development of artificial intelligence, AI…

In recent years, deep convolutional neural network (DCNN) has seen a breakthrough progress in natural image recognition because of three points: universal approximation ability via DCNN, large-scale database (such as ImageNet), and…

This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Our main goal…

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…

Image captioning has become an essential Vision & Language research task. It is about predicting the most accurate caption given a specific image or video. The research community has achieved impressive results by continuously proposing new…

Automated image-based garbage classification is a critical component of global waste management; however, systematic benchmarks that integrate Machine Learning (ML), Deep Learning (DL), and efficient hybrid solutions remain underdeveloped.…

Image colorization estimates RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality. Over the last decade, deep learning techniques for image colorization have significantly progressed,…

Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image…

In general, sufficient data is essential for the better performance and generalization of deep-learning models. However, lots of limitations(cost, resources, etc.) of data collection leads to lack of enough data in most of the areas. In…

In some scenarios, a single input image may not be enough to allow the object classification. In those cases, it is crucial to explore the complementary information extracted from images presenting the same object from multiple perspectives…

Recently, self-supervised metric learning has raised attention for the potential to learn a generic distance function. It overcomes the limitations of conventional supervised one, e.g., scalability and label biases. Despite progress in this…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost in classification. However, the performance is still limited because the scene images are mostly complex…

The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large,…