Related papers: Asymmetric Polynomial Loss For Multi-Label Classif…

Extractive summarization and imbalanced multi-label classification often require vast amounts of training data to avoid overfitting. In situations where training data is expensive to generate, leveraging information between tasks is an…

Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more balanced training loss and to improve tail classes data…

In computer vision, multi-label recognition are important tasks with many real-world applications, but classifying previously unseen labels remains a significant challenge. In this paper, we propose a novel algorithm, Aligned Dual moDality…

Active Learning for discriminative models has largely been studied with the focus on individual samples, with less emphasis on how classes are distributed or which classes are hard to deal with. In this work, we show that this is harmful.…

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same…

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…

An anomalous sound detection system to detect unknown anomalous sounds usually needs to be built using only normal sound data. Moreover, it is desirable to improve the system by effectively using a small amount of anomalous sound data,…

Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets.…

Medical image classification involves thresholding of labels that represent malignancy risk levels. Usually, a task defines a single threshold, and when developing computer-aided diagnosis tools, a single network is trained per such…

This letter considers optimizing user association in a heterogeneous network via utility maximization, which is a combinatorial optimization problem due to integer constraints. Different from existing solutions based on convex optimization,…

Categorizing individual cells into one of many known cell type categories, also known as cell type annotation, is a critical step in the analysis of single-cell genomics data. The current process of annotation is time-intensive and…

Class imbalance and the difficulty imbalance are the two types of data imbalance that affect the performance of neural networks in medical segmentation tasks. In class imbalance the loss is dominated by the majority classes and in…

Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency.…

In multi-task learning, labels are often missing irregularly across samples, which can be fully labeled, partially labeled or unlabeled. The irregular label presence often appears in scientific studies due to experimental limitations. It…

Wireless Capsule Endoscopy (WCE) helps physicians examine the gastrointestinal (GI) tract noninvasively. There are few studies that address pathological assessment of endoscopy images in multiclass classification and most of them are based…

We address the problem of distance metric learning in visual similarity search, defined as learning an image embedding model which projects images into Euclidean space where semantically and visually similar images are closer and dissimilar…

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same,…

Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and…

Multi-label classification is an important learning problem with many applications. In this work, we propose a principled similarity-based approach for multi-label learning called SML. We also introduce a similarity-based approach for…

The major challenge of learning from multi-label data has arisen from the overwhelming size of label space which makes this problem NP-hard. This problem can be alleviated by gradually involving easy to hard tags into the learning process.…