Related papers: Evaluating Multi-label Classifiers with Noisy Labels

Evaluating Multi-label Classifiers with Noisy Labels

URL: http://arxiv.org/abs/2102.08427v1
Date: Tue, 16 Feb 2021 19:50:52 GMT
Title: Evaluating Multi-label Classifiers with Noisy Labels
Authors: Wenting Zhao, Carla Gomes
Abstract summary: In the real world, it is more common to deal with noisy datasets than clean datasets. We present a Context-Based Multi-Label-Classifier (CbMLC) that effectively handles noisy labels. We show CbMLC yields substantial improvements over the previous methods in most cases.
Score: 0.7868449549351487
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Multi-label classification (MLC) is a generalization of standard classification where multiple labels may be assigned to a given sample. In the real world, it is more common to deal with noisy datasets than clean datasets, given how modern datasets are labeled by a large group of annotators on crowdsourcing platforms, but little attention has been given to evaluating multi-label classifiers with noisy labels. Exploiting label correlations now becomes a standard component of a multi-label classifier to achieve competitive performance. However, this component makes the classifier more prone to poor generalization - it overfits labels as well as label dependencies. We identify three common real-world label noise scenarios and show how previous approaches per-form poorly with noisy labels. To address this issue, we present a Context-Based Multi-LabelClassifier (CbMLC) that effectively handles noisy labels when learning label dependencies, without requiring additional supervision. We compare CbMLC against other domain-specific state-of-the-art models on a variety of datasets, under both the clean and the noisy settings. We show CbMLC yields substantial improvements over the previous methods in most cases.

Related papers

Label Cluster Chains for Multi-Label Classification [2.072831155509228]
Multi-label classification is a type of supervised machine learning that can simultaneously assign multiple labels to an instance. We propose a method to chain disjoint correlated label clusters obtained by applying a partition method in the label space. Our proposal shows that learning and chaining disjoint correlated label clusters can better explore and learn label correlations.
arXiv Detail & Related papers (2024-11-01T11:16:37Z)
Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification [85.76130799062379]
We study how false negative labels affect the model's explanation. We propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels.
arXiv Detail & Related papers (2023-04-04T14:00:59Z)
Complementary to Multiple Labels: A Correlation-Aware Correction Approach [65.59584909436259]
We show theoretically how the estimated transition matrix in multi-class CLL could be distorted in multi-labeled cases. We propose a two-step method to estimate the transition matrix from candidate labels.
arXiv Detail & Related papers (2023-02-25T04:48:48Z)
An Effective Approach for Multi-label Classification with Missing Labels [8.470008570115146]
We propose a pseudo-label based approach to reduce the cost of annotation without bringing additional complexity to the classification networks. By designing a novel loss function, we are able to relax the requirement that each instance must contain at least one positive label. We show that our method can handle the imbalance between positive labels and negative labels, while still outperforming existing missing-label learning approaches.
arXiv Detail & Related papers (2022-10-24T23:13:57Z)
Large Loss Matters in Weakly Supervised Multi-Label Classification [50.262533546999045]
We first regard unobserved labels as negative labels, casting the W task into noisy multi-label classification. We propose novel methods for W which reject or correct the large loss samples to prevent model from memorizing the noisy label. Our methodology actually works well, validating that treating large loss properly matters in a weakly supervised multi-label classification.
arXiv Detail & Related papers (2022-06-08T08:30:24Z)
Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [86.17081952197788]
We propose to blend category-specific representation across different images to transfer information of known labels to complement unknown labels. Experiments on the MS-COCO, Visual Genome, Pascal VOC 2007 datasets show that the proposed SARB framework obtains superior performance over current leading competitors.
arXiv Detail & Related papers (2022-03-04T07:56:16Z)
Weakly Supervised Classification Using Group-Level Labels [12.285265254225166]
We propose methods to use group-level binary labels as weak supervision to train instance-level binary classification models. We model group-level labels as Class Conditional Noisy (CCN) labels for individual instances and use the noisy labels to regularize predictions of the model trained on the strongly-labeled instances.
arXiv Detail & Related papers (2021-08-16T20:01:45Z)
A Study on the Autoregressive and non-Autoregressive Multi-label Learning [77.11075863067131]
We propose a self-attention based variational encoder-model to extract the label-label and label-feature dependencies jointly. Our model can therefore be used to predict all labels in parallel while still including both label-label and label-feature dependencies.
arXiv Detail & Related papers (2020-12-03T05:41:44Z)
Multi-Class Classification from Noisy-Similarity-Labeled Data [98.13491369929798]
We propose a method for learning from only noisy-similarity-labeled data. We use a noise transition matrix to bridge the class-posterior probability between clean and noisy data. We build a novel learning system which can assign noise-free class labels for instances.
arXiv Detail & Related papers (2020-02-16T05:10:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.