.png){kind=icon}
Return
Weakly supervised label learning flows
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2024.106892.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Supervised learning usually requires a large amount of labeled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that 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 LLF that trains the conditional flow inversely and avoids estimating the labels. Once a model is trained, 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.
Keywords:
Weakly supervised learning
Weakly supervised classification
Unpaired point cloud completion
Deep generative flows
Machine learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
8.2K
Citations:
3.0W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more