Related papers: ZeroLog: Zero-Label Generalizable Cross-System Log…

Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning…

Scene text recognition is a popular topic and extensively used in the industry. Although many methods have achieved satisfactory performance for the close-set text recognition challenges, these methods lose feasibility in open-set…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Semi-supervised anomaly detection methods leverage a few anomaly examples to yield drastically improved performance compared to unsupervised models. However, they still suffer from two limitations: 1) unlabeled anomalies (i.e., anomaly…

Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer…

Error detection (ED) in tabular data is crucial yet challenging due to diverse error types and the need for contextual understanding. Traditional ED methods often rely heavily on manual criteria and labels, making them labor-intensive.…

Most log-based anomaly detectors assume logs are stable, though logs are often unstable due to software or environmental changes. Anomaly detection on unstable logs (ULAD) is therefore a more realistic, yet under-investigated challenge.…

In-context learning refers to the emerging ability of large language models (LLMs) to perform a target task without additional training, utilizing demonstrations of the task. Recent studies aim to enhance in-context learning performance by…

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in…

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…

This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment…

A key requirement for supervised machine learning is labeled training data, which is created by annotating unlabeled data with the appropriate class. Because this process can in many cases not be done by machines, labeling needs to be…

Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited…

The Zero-Shot Learning (ZSL) task attempts to learn concepts without any labeled data. Unlike traditional classification/detection tasks, the evaluation environment is provided unseen classes never encountered during training. As such, it…

Metric learning is an important problem in machine learning. It aims to group similar examples together. Existing state-of-the-art metric learning approaches require class labels to learn a metric. As obtaining class labels in all…

Zero-shot learning (ZSL) aims to recognize unseen classes by leveraging semantic information from seen classes, but most existing methods assume accurate class labels for training instances. However, in real-world scenarios, noise and…

Intelligent equipment fault diagnosis based on Federated Transfer Learning (FTL) attracts considerable attention from both academia and industry. It allows real-world industrial agents with limited samples to construct a fault diagnosis…

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels, one of the big weaknesses of large audio datasets, and one…