paper-with-me

Papers

Active Learning for Structured Probabilistic Models With Histogram Approximation

2015-06-01 · CVPR 2015 6 · Qing Sun, Ankit Laddha, Dhruv Batra

Abstract. This paper studies active learning in structured probabilistic models such as Conditional Random Fields (CRFs). This is a challenging problem because unlike unstructured prediction problems such as binary or multi-class classification, structured prediction problems involve a distribution with an exponentially-large support, for instance, over the space of all possible segmentations of an image. Thus, the entropy of such models is typically intractable to compute. We propose a crude yet surprisingly effective histogram approximation to the Gibbs distribution, which replaces the exponentially-large support with a coarsened distribution that may be viewed as a histogram over M bins. We show that our approach outperforms a number of baselines and results in a 90%-reduction in the number of annotations needed to achieve nearly the same accuracy as learning from the entire dataset.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningGeneral ClassificationMulti-class ClassificationStructured Prediction

Similar Papers 제목 키워드 기반

Differentiable Histogram with Hard-Binning

2020-11-20 · Ibrahim Yusuf, George Igwegbe, Oluwafemi Azeez

The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed di…

Automatic Histograms: Leveraging Language Models for Text Dataset Exploration

2024-02-21 · Emily Reif, Crystal Qian, James Wexler, Minsuk Kahng

Making sense of unstructured text datasets is perennially difficult, yet increasingly relevant with Large Language Models. Data workers often rely on dataset summaries, especially distributions of various derived feature…

Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs

2022-02-17 · Stefano Teso, Antonio Vergari

In this position paper, we study interactive learning for structured output spaces, with a focus on active learning, in which labels are unknown and must be acquired, and on skeptical learning, in which the labels are no…

Active LearningPosition

Active Learning in Video Tracking

2019-12-29 · Sima Behpour

Active learning methods, like uncertainty sampling, combined with probabilistic prediction techniques have achieved success in various problems like image classification and text classification. For more complex multivar…

Active LearningComputational EfficiencyGeneral Classificationimage-classification+6

On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models

2023-05-27 · Boyao Li, Alexander J. Thomson, Houssam Nassif, Matthew M. Engelhard 외

Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative solution by constructing infinite tree-…

Gaussian Processes