paper-with-me

Papers

Pool-Based Active Learning with Proper Topological Regions

2023-10-02 · Lies Hadjadj, Emilie Devijver, Remi Molinier, Massih-Reza Amini

Machine learning methods usually rely on large sample size to have good performance, while it is difficult to provide labeled set in many applications. Pool-based active learning methods are there to detect, among a set of unlabeled data, the ones that are the most relevant for the training. We propose in this paper a meta-approach for pool-based active learning strategies in the context of multi-class classification tasks based on Proper Topological Regions. PTR, based on topological data analysis (TDA), are relevant regions used to sample cold-start points or within the active learning scheme. The proposed method is illustrated empirically on various benchmark datasets, being competitive to the classical methods from the literature.

📄 PDF Abstract BibTeX arXiv:2310.01597

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningMulti-class ClassificationTopological Data Analysis

Similar Papers 제목 키워드 기반

Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach

2024-07-16 · Tanvir Hossain, Khaled Mohammed Saifuddin, Muhammad Ifte Khairul Islam, Farhan Tanvir 외

Graph Neural Network (GNN) achieves great success for node-level and graph-level tasks via encoding meaningful topological structures of networks in various domains, ranging from social to biological networks. However, r…

Graph ClassificationGraph Neural Network

Topological Semantic Mapping by Consolidation of Deep Visual Features

2021-06-24 · Ygor C. N. Sousa, Hansenclever F. Bassani

Many works in the recent literature introduce semantic mapping methods that use CNNs (Convolutional Neural Networks) to recognize semantic properties in images. The types of properties (eg.: room size, place category, an…

Deep Graph Mapper: Seeing Graphs through the Neural Lens

2020-02-10 · NeurIPS Workshop TDA_and_Beyond 2020 12 · Cristian Bodnar, Cătălina Cangea, Pietro Liò

Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph. However, even though these abstract representations are powerful for down…

Graph ClassificationGraph Representation LearningRepresentation LearningTopological Data Analysis

NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation

2023-05-25 · Pengcheng Shi, Xutao Guo, Yanwu Yang, Chenfei Ye 외

Convolutional neural networks (CNN) and Transformer variants have emerged as the leading medical image segmentation backbones. Nonetheless, due to their limitations in either preserving global image context or efficientl…

Image SegmentationMedical Image SegmentationSemantic Segmentation

Retinal Vessel Segmentation Using A New Topological Method

2016-08-03 · Martin Brooks

A novel topological segmentation of retinal images represents blood vessels as connected regions in the continuous image plane, having shape-related analytic and geometric properties. This paper presents topological segm…

Retinal Vessel SegmentationSegmentation