paper-with-me

Papers Weakly Supervised Classification

“Weakly Supervised Classification” 태그가 달린 논문 40편 · 필터 해제

Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning

2026-03-05 · Rui Zhao, Bin Shi, Kai Sun, Bo Dong arxiv

Partial label learning is a prominent weakly supervised classification task, where each training instance is ambiguously labeled with a set of candidate labels. In real-world scenarios, candidate labels are often influen…

Weakly Supervised ClassificationPartial Label Learning

DSAGL: Dual-Stream Attention-Guided Learning for Weakly Supervised Whole Slide Image Classification

2025-05-29 · Daoxi Cao, Hangbei Cheng, Yijin Li, Ruolin Zhou 외

Whole-slide images (WSIs) are critical for cancer diagnosis due to their ultra-high resolution and rich semantic content. However, their massive size and the limited availability of fine-grained annotations pose substant…

image-classificationImage ClassificationWeakly Supervised Classificationwhole slide images

A Spatially-Aware Multiple Instance Learning Framework for Digital Pathology

2025-04-24 · Hassan Keshvarikhojasteh, Mihail Tifrea, Sibylle Hess, Josien P. W. Pluim 외

Multiple instance learning (MIL) is a promising approach for weakly supervised classification in pathology using whole slide images (WSIs). However, conventional MIL methods such as Attention-Based Deep Multiple Instance…

Computational EfficiencyMultiple Instance LearningWeakly Supervised Classificationwhole slide images

MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning

2024-08-21 · Minghao Han, Linhao Qu, Dingkang Yang, Xukun Zhang 외

Multiple instance learning (MIL) has become a standard paradigm for weakly supervised classification of whole slide images (WSI). However, this paradigm relies on the use of a large number of labelled WSIs for training. …

image-classificationImage ClassificationLanguage ModellingLarge Language Model+3

Reducing self-supervised learning complexity improves weakly-supervised classification performance in computational pathology

2024-03-07 · Tim Lenz, Omar S. M. El Nahhas, Marta Ligero, Jakob Nikolas Kather

Deep Learning models have been successfully utilized to extract clinically actionable insights from routinely available histology data. Generally, these models require annotations performed by clinicians, which are scarc…

ClassificationSelf-Supervised LearningWeakly Supervised Classification

RoFormer for Position Aware Multiple Instance Learning in Whole Slide Image Classification

2023-10-03 · Etienne Pochet, Rami Maroun, Roger Trullo

Whole slide image (WSI) classification is a critical task in computational pathology. However, the gigapixel-size of such images remains a major challenge for the current state of deep-learning. Current methods rely on m…

image-classificationImage ClassificationMultiple Instance LearningPosition+1

PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers

2023-08-19 · Wenhui Zhu, Peijie Qiu, Xiwen Chen, Oana M. Dumitrascu 외

Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. However, due to their weak supervision nature, the MIL metho…

Multiple Instance LearningWeakly Supervised ClassificationWeakly-supervised LearningWeakly Supervised Object Detection+1

CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification

2023-07-31 · ICCV 2023 1 · Rabab Abdelfattah, Qing Guo, Xiaoguang Li, XiaoFeng Wang 외

This paper presents a CLIP-based unsupervised learning method for annotation-free multi-label image classification, including three stages: initialization, training, and inference. At the initialization stage, we take fu…

Classificationimage-classificationImage ClassificationMulti-Label Image Classification+2

Kernel Density Matrices for Probabilistic Deep Learning

2023-05-26 · Fabio A. González, Raúl Ramos-Pollán, Joseph A. Gallego-Mejia

This paper introduces a novel approach to probabilistic deep learning, kernel density matrices, which provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and disc…

Deep LearningDensity Estimationimage-classificationImage Classification+2

CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images

2023-05-09 · Olga Fourkioti, Matt De Vries, Chen Jin, Daniel C. Alexander 외

The visual examination of tissue biopsy sections is fundamental for cancer diagnosis, with pathologists analyzing sections at multiple magnifications to discern tumor cells and their subtypes. However, existing attention…

DiagnosticImage ClassificationMultiple Instance LearningMultiple Instance LearningMultiple Instance Learning+2

Efficient subtyping of ovarian cancer histopathology whole slide images using active sampling in multiple instance learning

2023-02-17 · Jack Breen, Katie Allen, Kieran Zucker, Geoff Hall 외

Weakly-supervised classification of histopathology slides is a computationally intensive task, with a typical whole slide image (WSI) containing billions of pixels to process. We propose Discriminative Region Active Samp…

ClassificationCPUGPUMultiple Instance Learning+2

Easy Learning from Label Proportions

2023-02-06 · NeurIPS 2023 11

We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into "bags", and only the frequency of class labels at each bag is available. Albeit,…

Weakly Supervised Classification

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification

2022-12-11 · Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang

Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tas…

Classificationtext-classificationText ClassificationWeakly Supervised Classification

Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization

2022-10-16 · Jonathan Wilton, Abigail M. Y. Koay, Ryan K. L. Ko, Miao Xu 외

The need to learn from positive and unlabeled data, or PU learning, arises in many applications and has attracted increasing interest. While random forests are known to perform well on many tasks with positive and negati…

Feature ImportanceWeakly Supervised Classification

LIME: Weakly-Supervised Text Classification Without Seeds

2022-10-13 · COLING 2022 10 · Seongmin Park, Jihwa Lee

In weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framework, where test samples are first assign…

ClassificationNatural Language Inferencetext-classificationText Classification+1

Label Propagation with Weak Supervision

2022-10-07 · Rattana Pukdee, Dylan Sam, Maria-Florina Balcan, Pradeep Ravikumar

Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications. In this paper, we introduce a novel analysi…

Weakly Supervised ClassificationWeakly-supervised Learning

Class-Imbalanced Complementary-Label Learning via Weighted Loss

2022-09-28 · Meng Wei, Yong Zhou, Zhongnian Li, Xinzheng Xu

Complementary-label learning (CLL) is widely used in weakly supervised classification, but it faces a significant challenge in real-world datasets when confronted with class-imbalanced training samples. In such scenarios…

Multi-class ClassificationWeakly Supervised Classification

Weakly Supervised Classification of Vital Sign Alerts as Real or Artifact

2022-06-18 · Arnab Dey, Mononito Goswami, Joo Heung Yoon, Gilles Clermont 외

A significant proportion of clinical physiologic monitoring alarms are false. This often leads to alarm fatigue in clinical personnel, inevitably compromising patient safety. To combat this issue, researchers have attemp…

Weakly Supervised Classification

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

Importance of Textlines in Historical Document Classification

2022-01-24 · Martin Kišš, Jan Kohút, Karel Beneš, Michal Hradiš

This paper describes a system prepared at Brno University of Technology for ICDAR 2021 Competition on Historical Document Classification, experiments leading to its design, and the main findings. The solved tasks include…

ClassificationDocument ClassificationWeakly Supervised Classification
1–20 / 40 다음 →