paper-with-me

Papers

Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags

2024-08-26 · Shunsuke Kubo, Shinnosuke Matsuo, Daiki Suehiro, Kazuhiro Terada, Hiroaki Ito, Akihiko Yoshizawa, Ryoma Bise

Learning from label proportions (LLP) is a kind of weakly supervised learning that trains an instance-level classifier from label proportions of bags, which consist of sets of instances without using instance labels. A challenge in LLP arises when the number of instances in a bag (bag size) is numerous, making the traditional LLP methods difficult due to GPU memory limitations. This study aims to develop an LLP method capable of learning from bags with large sizes. In our method, smaller bags (mini-bags) are generated by sampling instances from large-sized bags (original bags), and these mini-bags are used in place of the original bags. However, the proportion of a mini-bag is unknown and differs from that of the original bag, leading to overfitting. To address this issue, we propose a perturbation method for the proportion labels of sampled mini-bags to mitigate overfitting to noisy label proportions. This perturbation is added based on the multivariate hypergeometric distribution, which is statistically modeled. Additionally, loss weighting is implemented to reduce the negative impact of proportions sampled from the tail of the distribution. Experimental results demonstrate that the proportion label perturbation and loss weighting achieve classification accuracy comparable to that obtained without sampling. Our codes are available at https://github.com/stainlessnight/LLP-LargeBags.

📄 PDF Abstract BibTeX arXiv:2408.14130

Code (1)

stainlessnight/llp-largebags 공식 구현 pytorch

Tasks

GPUWeakly-supervised Learning

Similar Papers 제목 키워드 기반

Learning from Label Proportions by Learning with Label Noise

2022-03-04 · Jianxin Zhang, Yutong Wang, Clayton Scott

Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels. Th…

Weakly Supervised Classification

Learning from Partial Label Proportions for Whole Slide Image Segmentation

2024-05-15 · Shinnosuke Matsuo, Daiki Suehiro, Seiichi Uchida, Hiroaki Ito 외

In this paper, we address the segmentation of tumor subtypes in whole slide images (WSI) by utilizing incomplete label proportions. Specifically, we utilize `partial' label proportions, which give the proportions among t…

DiagnosticImage SegmentationMultiple Instance LearningSemantic Segmentation+2

On Learning from Label Proportions

2014-02-24 · Felix X. Yu, Krzysztof Choromanski, Sanjiv Kumar, Tony Jebara 외

Learning from Label Proportions (LLP) is a learning setting, where the training data is provided in groups, or "bags", and only the proportion of each class in each bag is known. The task is to learn a model to predict t…

Marketing

Deep multi-class learning from label proportions

2019-05-30 · Gabriel Dulac-Arnold, Neil Zeghidour, Marco Cuturi, Lucas Beyer 외

We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each labe…

Binary ClassificationGeneral Classificationimage-classificationImage Classification

MixBag: Bag-Level Data Augmentation for Learning from Label Proportions

2023-08-17 · ICCV 2023 1 · Takanori Asanomi, Shinnosuke Matsuo, Daiki Suehiro, Ryoma Bise

Learning from label proportions (LLP) is a promising weakly supervised learning problem. In LLP, a set of instances (bag) has label proportions, but no instance-level labels are given. LLP aims to train an instance-level…

Data AugmentationWeakly-supervised Learning