paper-with-me

Papers

Weakly Supervised Clustering by Exploiting Unique Class Count

2019-06-18 · ICLR 2020 1 · Mustafa Umit Oner, Hwee Kuan Lee, Wing-Kin Sung

A weakly supervised learning based clustering framework is proposed in this paper. As the core of this framework, we introduce a novel multiple instance learning task based on a bag level label called unique class count ($ucc$), which is the number of unique classes among all instances inside the bag. In this task, no annotations on individual instances inside the bag are needed during training of the models. We mathematically prove that with a perfect $ucc$ classifier, perfect clustering of individual instances inside the bags is possible even when no annotations on individual instances are given during training. We have constructed a neural network based $ucc$ classifier and experimentally shown that the clustering performance of our framework with our weakly supervised $ucc$ classifier is comparable to that of fully supervised learning models where labels for all instances are known. Furthermore, we have tested the applicability of our framework to a real world task of semantic segmentation of breast cancer metastases in histological lymph node sections and shown that the performance of our weakly supervised framework is comparable to the performance of a fully supervised Unet model.

📄 PDF Abstract BibTeX arXiv:1906.07647

Code (1)

howard-hou/UniqueClassCount pytorch

Tasks

ClusteringMultiple Instance LearningSemantic SegmentationWeakly-supervised LearningZero-Shot Learning

Similar Papers 제목 키워드 기반

Learning Temporal Co-Attention Models for Unsupervised Video Action Localization

2020-06-01 · CVPR 2020 6 · Guoqiang Gong, Xinghan Wang, Yadong Mu, Qi Tian

Temporal action localization (TAL) in untrimmed videos recently receives tremendous research enthusiasm. To our best knowledge, this is the first attempt in the literature to explore this task under an unsupervised setti…

Action LocalizationClusteringTemporal Action LocalizationTriplet

Weakly-Supervised Semantic Segmentation via Sub-category Exploration

2020-08-03 · CVPR 2020 6 · Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu 외

Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usu…

ClusteringObjectSemantic SegmentationWeakly supervised Semantic Segmentation+1

Weakly supervised clustering: Learning fine-grained signals from coarse labels

2013-10-04 · Stefan Wager, Alexander Blocker, Niall Cardin

Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a cla…

ClassificationClusteringGeneral Classification

Weakly-Supervised Dual Clustering for Image Semantic Segmentation

2013-06-01 · CVPR 2013 6 · Yang Liu, Jing Liu, Zechao Li, Jinhui Tang 외

In this paper, we propose a novel Weakly-Supervised Dual Clustering (WSDC) approach for image semantic segmentation with image-level labels, i.e., collaboratively performing image segmentation and tag alignment with thos…

ClusteringImage SegmentationSegmentationSemantic Segmentation+2

Weakly Supervised Deep Detection Networks

2015-11-09 · CVPR 2016 6 · Hakan Bilen, Andrea Vedaldi

Weakly supervised learning of object detection is an important problem in image understanding that still does not have a satisfactory solution. In this paper, we address this problem by exploiting the power of deep convo…

ClassificationData AugmentationGeneral ClassificationObject+4