methodology-4

Partial Label Learning

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in partial-label-learning-4

Trend

Dataset

Best Model

Actions

Autoimmune Dataset

M-VAD Names

MPII Movie Description

Libraries

i

Use these libraries to find partial-label-learning-4 models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

Exploiting Class Activation Value for Partial-Label Learning

Tongliang Liu, Masashi Sugiyama, Bo Han, Gang Niu, Fei Zhang, Lei Feng, Tao Qin•Fri Dec 31 2021

This paper proposes the class activation value (CAV), which owns similar properties of CAM, while CAV is versatile in various types of inputs and models, and proposes a novel method named CAV Learning (CAVL) that selects the true label by the class with the maximum CAV for model training.

59

Content

MPII Movie Description

ISIC 2019

CIFAR-10 (partial ratio 0.1)

CIFAR-10 (partial ratio 0.3)

CIFAR-10 (partial ratio 0.5)

CIFAR-100 (partial ratio 0.01)

CIFAR-100 (partial ratio 0.05)

CIFAR-100 (partial ratio 0.1)

Caltech-UCSD Birds 200 (partial ratio 0.05)

0

Paper Graph

Towards Mitigating the Class-Imbalance Problem for Partial Label Learning

Min-Ling Zhang, Jing Wang•Wed Jul 18 2018

Extensive experiments on artificial as well as real-world PL data sets show that CIMAP serves as an effective data-level approach to mitigate the class-imbalance problem for partial label learning.

28 0

Paper Graph

On The Power of Deep But Naive Partial Label Learning

Junghoon Seo, J. Huh•Wed Oct 21 2020

It is shown that, with deep neural networks, the naive model can achieve competitive performances against the other state-of-the-art methods, suggesting it as a strong baseline for PLL and proposes an alternative theory on how deep learning generalize in PLL problems.

12 0

Paper Graph

OPAM: Online Purchasing-behavior Analysis using Machine learning

Sohini Roychowdhury, Ebrahim Alareqi•Mon Feb 01 2021

The proposed system analyzes session and user-journey level purchasing behaviors to identify customer categories/clusters that can be useful for targeted consumer insights at scale and demonstrates the robustness of each user cluster to new/unlabelled events.

9 0

Paper Graph

Progressive Identification of True Labels for Partial-Label Learning

Masashi Sugiyama, Gang Niu, Miao Xu, Xin Geng, Lei Feng, Jiaqi Lv•Tue Feb 18 2020

A novel estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound are proposed, and a progressive identification algorithm for approximately minimizing the proposed risk estimator is proposed.

211 0

Paper Graph

Leveraged Weighted Loss for Partial Label Learning

Zhouchen Lin, Hongwei Wen, Jingyi Cui, H. Hang, Jiabin Liu, Yisen Wang•Wed Jun 09 2021

A family of loss functions is proposed, which for the first time introduces the leverage parameter $\beta$ to consider the trade-off between losses on partial labels and non-partial ones and derives a generalized result of risk consistency for the LW loss in learning from partial labels.

112 0

Paper Graph

Instance-Dependent Partial Label Learning

Ning Xu, Xin Geng, Congyu Qiao, Min-Ling Zhang•Sun Oct 24 2021

This paper considers instance-dependent PLL and assumes that the generation process of the candidate labels could decompose into two sequential parts, where the correct label emerges first in the mind of the annotator but then the incorrect labels related to the feature are also selected with the correct Label due to uncertainty of labeling.

99 0

Paper Graph

PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning

J. Zhao, Gang Niu, Yixuan Li, Lei Feng, Haobo Wang, Rui Xiao, Gang Chen•Fri Jan 21 2022

This work develops a novel label disambiguation algorithm PiCO that consists of a contrastive learning module along with a novel class prototype-based disambiguation method that can be rigorously justified from an expectation-maximization (EM) algorithm perspective.

40 0

Paper Graph

Webly-Supervised Fine-Grained Recognition with Partial Label Learning

Xiu-Shen Wei, Yu-yan Xu, Yang Shen•Thu Jun 30 2022

This paper utilizes a pre-trained deep model to perform deep descriptor transformation to estimate the positive correlation between these web images, and detects the open-set noises based on the correlation values, and develops a top-k recall optimization loss for firstly assigning a label set towards each web image to reduce the impact of hard label assignment for closed- set noises.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.