Related papers: Label Forensics: Interpreting Hard Labels in Black…

The crux of label-efficient semantic segmentation is to produce high-quality pseudo-labels to leverage a large amount of unlabeled or weakly labeled data. A common practice is to select the highly confident predictions as the…

Fine-grained multi-label classification models have broad applications in e-commerce, such as visual based label predictions ranging from fashion attribute detection to brand recognition. One challenge to achieve satisfactory performance…

Research in emotion analysis is scattered across different label formats (e.g., polarity types, basic emotion categories, and affective dimensions), linguistic levels (word vs. sentence vs. discourse), and, of course, (few well-resourced…

We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels. Given a set of class labels, a category taxonomy is automatically learned by collectively optimizing a clustering…

Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems, particularly focusing on word embeddings. Key topics include the construction of categories $\mathcal{L}_T$…

Technological and computational advances continuously drive forward the broad field of deep learning. In recent years, the derivation of quantities describing theuncertainty in the prediction - which naturally accompanies the modeling…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

Recent advances in large language models enable documents to be represented as dense semantic embeddings, supporting similarity-based operations over large text collections. However, many web-scale systems still rely on flat clustering or…

In machine learning, one must acquire labels to help supervise a model that will be able to generalize to unseen data. However, the labeling process can be tedious, long, costly, and error-prone. It is often the case that most of our data…

Word embeddings typically represent different meanings of a word in a single conflated vector. Empirical analysis of embeddings of ambiguous words is currently limited by the small size of manually annotated resources and by the fact that…

Since the rise of deep learning, many computer vision tasks have seen significant advancements. However, the downside of deep learning is that it is very data-hungry. Especially for segmentation problems, training a deep neural net requires…

Semantic communication is an emerging paradigm that focuses on understanding and delivering semantics, or meaning of messages. Most existing semantic communication solutions define semantic meaning as the meaning of object labels recognized…

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation,…

Deep learning approaches exhibit promising performances on various text tasks. However, they are still struggling on medical text classification since samples are often extremely imbalanced and scarce. Different from existing mainstream…

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded…

In this paper, we investigate the effect of addressing difficult samples from a given text dataset on the downstream text classification task. We define difficult samples as being non-obvious cases for text classification by analysing them…

Code search and comprehension have become more difficult in recent years due to the rapid expansion of available source code. Current tools lack a way to label arbitrary code at scale while maintaining up-to-date representations of new…

Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation…