paper-with-me

Papers

MoBYv2AL: Self-supervised Active Learning for Image Classification

2023-01-04 · Razvan Caramalau, Binod Bhattarai, Danail Stoyanov, Tae-Kyun Kim

Active learning(AL) has recently gained popularity for deep learning(DL) models. This is due to efficient and informative sampling, especially when the learner requires large-scale labelled datasets. Commonly, the sampling and training happen in stages while more batches are added. One main bottleneck in this strategy is the narrow representation learned by the model that affects the overall AL selection. We present MoBYv2AL, a novel self-supervised active learning framework for image classification. Our contribution lies in lifting MoBY, one of the most successful self-supervised learning algorithms, to the AL pipeline. Thus, we add the downstream task-aware objective function and optimize it jointly with contrastive loss. Further, we derive a data-distribution selection function from labelling the new examples. Finally, we test and study our pipeline robustness and performance for image classification tasks. We successfully achieved state-of-the-art results when compared to recent AL methods. Code available: https://github.com/razvancaramalau/MoBYv2AL

📄 PDF Abstract BibTeX arXiv:2301.01531

Code (1)

razvancaramalau/mobyv2al 공식 구현 pytorch

Tasks

Active LearningClassificationimage-classificationImage ClassificationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BYOL 설명 없음
InfoNCE 설명 없음
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
DropPath Just as dropout prevents co-adaptation of activations, DropPath prevents co-adaptation of parallel paths in networks such as…
MoCo v2 MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Motivated by the findings presented in…

Similar Papers 제목 키워드 기반

Active Learning Guided Fine-Tuning for enhancing Self-Supervised Based Multi-Label Classification of Remote Sensing Images

2023-06-12 · Lars Möllenbrok, Begüm Demir

In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly select…

Active LearningMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation

2021-04-13 · Dwarikanath Mahapatra

In supervised learning for medical image analysis, sample selection methodologies are fundamental to attain optimum system performance promptly and with minimal expert interactions (e.g. label querying in an active learn…

Active LearningGeneral ClassificationImage SegmentationInformativeness+4

PT4AL: Using Self-Supervised Pretext Tasks for Active Learning

2022-01-19 · John Seon Keun Yi, Minseok Seo, Jongchan Park, Dong-Geol Choi

Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilize…

Active Learningimage-classificationImage Classification

ActiveSSF: An Active-Learning-Guided Self-Supervised Framework for Long-Tailed Megakaryocyte Classification

2025-02-12 · Linghao Zhuang, Ying Zhang, Gege Yuan, Xingyue Zhao 외

Precise classification of megakaryocytes is crucial for diagnosing myelodysplastic syndromes. Although self-supervised learning has shown promise in medical image analysis, its application to classifying megakaryocytes i…

Active LearningClusteringMedical Image AnalysisSelf-Supervised Learning

Active Self-Semi-Supervised Learning for Few Labeled Samples

2022-03-09 · Ziting Wen, Oscar Pizarro, Stefan Williams

Training deep models with limited annotations poses a significant challenge when applied to diverse practical domains. Employing semi-supervised learning alongside the self-supervised model offers the potential to enhanc…

Active Learningimage-classificationImage ClassificationSelf-Supervised Learning