paper-with-me

홈 › Papers

ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision

2022-04-14 · Anastasiia Sedova, Benjamin Roth

A cost-effective alternative to manual data labeling is weak supervision (WS), where data samples are automatically annotated using a predefined set of labeling functions (LFs), rule-based mechanisms that generate artificial labels for the associated classes. In this work, we investigate noise reduction techniques for WS based on the principle of k-fold cross-validation. We introduce a new algorithm ULF for Unsupervised Labeling Function correction, which denoises WS data by leveraging models trained on all but some LFs to identify and correct biases specific to the held-out LFs. Specifically, ULF refines the allocation of LFs to classes by re-estimating this assignment on highly reliable cross-validated samples. Evaluation on multiple datasets confirms ULF's effectiveness in enhancing WS learning without the need for manual labeling.

📄 PDF Abstract BibTeX arXiv:2204.06863

Code (1)

knodle/knodle 공식 구현 pytorch

Tasks

DenoisingWeakly-supervised Learning

Similar Papers 제목 키워드 기반

Unsupervised Visible-Infrared ReID via Pseudo-label Correction and Modality-level Alignment

2024-04-10 · Yexin Liu, Weiming Zhang, Athanasios V. Vasilakos, Lin Wang

Unsupervised visible-infrared person re-identification (UVI-ReID) has recently gained great attention due to its potential for enhancing human detection in diverse environments without labeling. Previous methods utilize …

ClusteringContrastive LearningCross-Modality Person Re-identificationHuman Detection+2

Unsupervised domain adaptation for speech recognition with unsupervised error correction

2022-09-24 · Long Mai, Julie Carson-Berndsen

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderDomain Adaptation+3

Improving zero-shot learning by mitigating the hubness problem

2014-12-20 · Georgiana Dinu, Angeliki Lazaridou, Marco Baroni

The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associ…

Image RetrievalRetrievalZero-Shot Learning

CLIP-Guided Unsupervised Semantic-Aware Exposure Correction

2026-01-27 · Puzhen Wu, Han Weng, Quan Zheng, Yi Zhan 외 arxiv

Improper exposure often leads to severe loss of details, color distortion, and reduced contrast. Exposure correction still faces two critical challenges: (1) the ignorance of object-wise regional semantic information cau…

Error correction and extraction in request dialogs

2020-04-08 · Stefan Constantin, Alex Waibel

We propose a dialog system utility component that gets the last two utterances of a user and can detect whether the last utterance is an error correction of the second last utterance. If yes, it corrects the second last …