Constrained Labeling for Weakly Supervised Learning
Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling functions from varying sources. The key challenge in weakly supervised learning is combining the different weak supervision signals while navigating misleading correlations in their errors. In this paper, we propose a simple data-free approach for combining weak supervision signals by defining a constrained space for the possible labels of the weak signals and training with a random labeling within this constrained space. Our method is efficient and stable, converging after a few iterations of gradient descent. We prove theoretical conditions under which the worst-case error of the randomized label decreases with the rank of the linear constraints. We show experimentally that our method outperforms other weak supervision methods on various text- and image-classification tasks.
Code (1)
Tasks
image-classificationImage ClassificationWeakly-supervised LearningSimilar Papers 제목 키워드 기반
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constraine…
Image SegmentationSemantic SegmentationTAGWeakly supervised segmentationWeakly Supervised Label Learning Flows
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 appr…
Weakly-supervised LearningLearning from Reduced Labels for Long-Tailed Data
Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite b…
Weakly-supervised LearningBudget-aware Semi-Supervised Semantic and Instance Segmentation
Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker fo…
Image SegmentationInstance SegmentationSegmentationSemantic SegmentationUncertainty Based Active Learning Strategy for Interactive Weakly Supervised Learning through Data Programming
Easy to build and reliable machine learning models are what all data analysts want. Although machine learning is advancing daily, the labeling cost for supervised learning and the black-box nature of machine learning are…
Active LearningBIG-bench Machine Learningtext-classificationText Classification+1