paper-with-me

Papers

Weakly Supervised Label Learning Flows

2023-02-19 · You Lu, Wenzhuo Song, Chidubem Arachie, Bert Huang

Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some data. Many existing weakly supervised learning methods learn a deterministic function that estimates labels given the input data and weak signals. In this paper, we develop label learning flows (LLF), a general framework for weakly supervised learning problems. Our method is a generative model based on normalizing flows. The main idea of LLF is to optimize the conditional likelihoods of all possible labelings of the data within a constrained space defined by weak signals. We develop a training method for LLF that trains the conditional flow inversely and avoids estimating the labels. Once a model is trained, we can make predictions with a sampling algorithm. We apply LLF to three weakly supervised learning problems. Experiment results show that our method outperforms many baselines we compare against.

📄 PDF Abstract BibTeX arXiv:2302.09649

Code (1)

yolu1055/weakly-supervised-label-learning-flow 공식 구현 pytorch

Tasks

Weakly-supervised Learning

Similar Papers 제목 키워드 기반

Structure Label Prediction Using Similarity-Based Retrieval and Weakly-Supervised Label Mapping

2019-05-16 · Yazeed Alaudah, Motaz Alfarraj, Ghassan AlRegib

Recently, there has been significant interest in various supervised machine learning techniques that can help reduce the time and effort consumed by manual interpretation workflows. However, most successful supervised ma…

BIG-bench Machine LearningRetrievalSeismic Interpretation

Tracking Indistinguishable Translucent Objects over Time using Weakly Supervised Structured Learning

2014-06-01 · CVPR 2014 6 · Luca Fiaschi, Ferran Diego, Konstantin Gregor, Martin Schiegg 외

We use weakly supervised structured learning to track and disambiguate the identity of multiple indistinguishable, translucent and deformable objects that can overlap for many frames. For this challenging problem, we pro…

Guided Prompting in SAM for Weakly Supervised Cell Segmentation in Histopathological Images

2023-11-29 · Aayush Kumar Tyagi, Vaibhav Mishra, Prathosh A. P., Mausam

Cell segmentation in histopathological images plays a crucial role in understanding, diagnosing, and treating many diseases. However, data annotation for this is expensive since there can be a large number of cells per i…

Cell SegmentationImage SegmentationSegmentationSemantic Segmentation

WeaNF: Weak Supervision with Normalizing Flows

2022-04-28 · Andreas Stephan, Benjamin Roth

A popular approach to decrease the need for costly manual annotation of large data sets is weak supervision, which introduces problems of noisy labels, coverage and bias. Methods for overcoming these problems have either…

WeaNF: Weak Supervision with Normalizing Flows

2021-11-16 · ACL ARR November 2021 11 · Anonymous

A popular approach to decrease the need for costly manual annotation of large data sets is weak supervision, which introduces problems of noisy labels, coverage and bias. Methods for overcoming these problems have either…