Related papers: ReMarNet: Conjoint Relation and Margin Learning fo…

Traditional deep learning-based object detection networks often resize images during the data preprocessing stage to achieve a uniform size and scale in the feature map. Resizing is done to facilitate model propagation and fully connected…

Semi-supervised learning has received a lot of recent attention as it alleviates the need for large amounts of labelled data which can often be expensive, requires expert knowledge and be time consuming to collect. Recent developments in…

We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image elements to feature…

The caliber and configuration of retinal blood vessels serve as important biomarkers for various diseases and medical conditions. A thorough analysis of the retinal vasculature requires the segmentation of the blood vessels and their…

ResNets and its variants play an important role in various fields of image recognition. This paper gives another variant of ResNets, a kind of cross-residual learning networks called C-ResNets, which has less computation and parameters than…

With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal…

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…

This paper proposes a branched residual network for image classification. It is known that high-level features of deep neural network are more representative than lower-level features. By sharing the low-level features, the network can…

In the context of few-shot classification, the goal is to train a classifier using a limited number of samples while maintaining satisfactory performance. However, traditional metric-based methods exhibit certain limitations in achieving…

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to…

Supervised learning from training data with imbalanced class sizes, a commonly encountered scenario in real applications such as anomaly/fraud detection, has long been considered a significant challenge in machine learning. Motivated by…

Deep-learning-based local feature extraction algorithms that combine detection and description have made significant progress in visible image matching. However, the end-to-end training of such frameworks is notoriously unstable due to the…

Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown…

Deep learning has revolutionized various fields, yet its efficacy is hindered by overfitting and the requirement of extensive annotated data, particularly in few-shot learning scenarios where limited samples are available. This paper…

Recently, deep learning techniques have been extensively studied for pansharpening, which aims to generate a high resolution multispectral (HRMS) image by fusing a low resolution multispectral (LRMS) image with a high resolution…

Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with traditional methods.…

Ability of deep networks to extract high level features and of recurrent networks to perform time-series inference have been studied. In view of universality of one hidden layer network at approximating functions under weak constraints, the…

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information…