Bi-directional Representation Learning for Multi-label Classification

Li, Xin; Guo, Yuhong

doi:10.1007/978-3-662-44851-9_14

Cited by 8 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A naïve approach to uncertainty-diversity active learning is to use a weighted combination of uncertainty scores and diversity metrics to select samples. [57][58][59] In their work, Rodriguez et al 59 propose a novel acquisition function for batches of data that contain a sum of both uncertainty and diversity weights. Kirsch, Van Amersfoort, and Gal 60 instead use a modified version of uncertainty scoring, taking the Mutual Information of the whole batch in order to maximize diversity of samples selected together.…”

Section: Uncertainty-diversity Hybrid Active Learning Methodsmentioning

confidence: 99%

Diversity-based active learning: creating a representative object detection dataset in 3D point clouds

Moses

Bogart

O'Haire

et al. 2023

Geospatial Informatics XIII

View full text Add to dashboard Cite

Object detection in 3D point clouds is essential in fields such as geospatial intelligence and autonomous driving. The common machine learning problem of scarce labeled training data is even more acute with 3D point cloud data. Active learning provides a framework to prioritize the additional effort to manually annotate unlabeled training data. Most active learning methods for deep learning fall into one of two categories: uncertainty methods and diversity methods. Uncertainty methods select data by assessing model outputs for their confidence and consistency and are therefore dependent on the expected output of each deep learning task. These methods tend to select batches of informative yet highly similar samples to label. Diversity-based active learning aims to create a labeled dataset that is both varied and representative of the remaining unlabeled data. Diversity methods operate directly on the feature representations of the inputs and are thus more flexible with respect to the specifics of the deep learning task. Our current work explores applying diversity methods and uncertainty-diversity hybrid methods to 3D object detection. We evaluate various approaches to incorporate diversity, including K-Medoids clustering, core set selection, and furthest nearest neighbors. We address the high dimensionality of the features extracted from a VoxelNet-based object detector by varying the distance metric used in the active learning algorithms. Furthermore, we compare our results to those obtained using only uncertainty methods. We assess the performance and efficiency of each active learning method in addition to the representativeness and diversity of the labeled datasets produced. We find that hybrid uncertainty-diversity methods outperform other methods in terms of object detection AP50 throughout active learning, annotation efficiency, and class balance.

show abstract

Section: Uncertainty-diversity Hybrid Active Learning Methodsmentioning

confidence: 99%

Diversity-based active learning: creating a representative object detection dataset in 3D point clouds

Moses

Bogart

O'Haire

et al. 2023

Geospatial Informatics XIII

View full text Add to dashboard Cite

show abstract

“…1) A reconstruction model Ψ inv : y ′ → y is trained during the reduction phase or after [53]. It allows to reconstruct y from y ′ in the test phase.…”

Section: Label Space Reduction (Y)mentioning

confidence: 99%

“…A major part of the algorithms impose the minimization of the L 2 -norm of the parameters. This benefits solutions with low-value parameters[53] [29].…”

mentioning

confidence: 99%

A Review on Dimensionality Reduction for Multi-label Classification

Siblini

Kuntz

Meyer

2019

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Multi-label classification has gained in importance in the last decade and it is today confronted to the current needs to process massive raw data from heterogeneous sources. Therefore, dimensionality reduction, which aims at reducing the number of features, labels, or both, knows a renewed interest to enhance the scaling properties of the classifiers and their predictive performances. In this paper we review more than fifty papers presenting dimensionality reduction approaches for multi-label classification and we propose an analysis in three steps : (i) a typology of the methods describing the main components of their strategies, the problem they tackle and the way they solve it (ii) a unified formalization of the problems to help to distinguish the similarities and differences between the approaches, and (iii) a meta-analysis of the published experimental results inspired by the consensus theory to identify the most efficient algorithms.

show abstract

“…However, current works about representation learning neglect label knowledge, or suffer from the lack of labeled data, or are limited to linear projection. The most related work (Li and Guo 2014), which proposed a bi-directional representation model for multi-label classification, in which the mid-level representation layer is constructed from both input and output spaces. In essence, their network structure is different from ours.…”

Section: Effects On Supervision Informationmentioning

confidence: 99%

Supervised representation learning for multi-label classification

et al. 2019

View full text Add to dashboard Cite

Representation learning is one of the most important aspects of multi-label learning because of the intricate nature of multi-label data. Current research on representation learning either fails to consider label knowledge or is affected by the lack of labeled data. Moreover, most of them learn the representations and incorporate the label information in a two-step manner. In this paper, due to the success of representation learning by deep learning we propose a novel framework based on neural networks named SERL to learn global feature representation by jointly considering all labels in an effective supervised manner. At its core, a two-encodinglayer autoencoder, which can utilize labeled and unlabeled data, is adopted to learn feature representation in the supervision of softmax regression. Specifically, the softmax regression incorporates label knowledge to improve the performance of both representation learning and multi-label learning by being jointly optimized with the autoencoder. Moreover, the autoencoder is expanded into two encoding layers to share knowledge with the softmax regression by sharing the second encoding weight matrix. We conduct extensive experiments on five real-world datasets to demonstrate the superiority of SERL over other state-of-the-art multi-label learning approaches.

show abstract

Bi-directional Representation Learning for Multi-label Classification

Cited by 8 publications

References 18 publications

Diversity-based active learning: creating a representative object detection dataset in 3D point clouds

Diversity-based active learning: creating a representative object detection dataset in 3D point clouds

A Review on Dimensionality Reduction for Multi-label Classification

Supervised representation learning for multi-label classification

Contact Info

Product

Resources

About