Related papers: Group Preserving Label Embedding for Multi-Label C…
Point feature map labeling is a geometric problem, in which a set of input points must be labeled with a set of disjoint rectangles (the bounding boxes of the label texts). Typically, labeling models either use internal labels, which must…
In recent years, multi-label classification has attracted a significant body of research, motivated by real-life applications, such as text classification and medical diagnoses. Although sparsely studied in this context, Learning Classifier…
A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with…
We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…
This work proposes a novel method for semi-supervised learning from partially labeled massive network-structured datasets, i.e., big data over networks. We model the underlying hypothesis, which relates data points to labels, as a graph…
We investigate the integration of word embeddings as classification features in the setting of large scale text classification. Such representations have been used in a plethora of tasks, however their application in classification…
Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected…
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…
Systematic mislabelling affecting specific subgroups (i.e., label bias) in medical imaging datasets represents an understudied issue concerning the fairness of medical AI systems. In this work, we investigated how size and separability of…
Annotating data for multi-label classification is prohibitively expensive because every category of interest must be confirmed to be present or absent. Recent work on single positive multi-label (SPML) learning shows that it is possible to…
Collecting labeled data to train deep neural networks is costly and even impractical for many tasks. Thus, research effort has been focused in automatically curated datasets or unsupervised and weakly supervised learning. The common problem…
Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning, semi-supervised learning and active learning, aim to be…
Multi-label learning deals with the problem that each instance is associated with multiple labels simultaneously. Most of the existing approaches aim to improve the performance of multi-label learning by exploiting label correlations.…
Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains. However, the high dimensionality of sparse data in recommendation tasks and the huge volume of…
With the rapid growth of web images, hashing has received increasing interests in large scale image retrieval. Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels. However,…
Multi-label few-shot image classification (ML-FSIC) is the task of assigning descriptive labels to previously unseen images, based on a small number of training examples. A key feature of the multi-label setting is that images often have…
Semantic labeling for numerical values is a task of assigning semantic labels to unknown numerical attributes. The semantic labels could be numerical properties in ontologies, instances in knowledge bases, or labeled data that are manually…
The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient…
State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…
Being able to model correlations between labels is considered crucial in multi-label classification. Rule-based models enable to expose such dependencies, e.g., implications, subsumptions, or exclusions, in an interpretable and…