Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction
- URL: http://arxiv.org/abs/2307.09004v2
- Date: Fri, 21 Jul 2023 08:41:23 GMT
- Title: Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction
- Authors: Jinhong Wang, Yi Cheng, Jintai Chen, Tingting Chen, Danny Chen and
Jian Wu
- Abstract summary: We propose a simple sequence prediction framework for ordinal regression called Ord2Seq.
We decompose an ordinal regression task into a series of binary classification steps, so as to subtly distinguish adjacent categories.
Our new approach exceeds state-of-the-art performances in four different scenarios.
- Score: 13.844821175622794
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Ordinal regression refers to classifying object instances into ordinal
categories. It has been widely studied in many scenarios, such as medical
disease grading, movie rating, etc. Known methods focused only on learning
inter-class ordinal relationships, but still incur limitations in
distinguishing adjacent categories thus far. In this paper, we propose a simple
sequence prediction framework for ordinal regression called Ord2Seq, which, for
the first time, transforms each ordinal category label into a special label
sequence and thus regards an ordinal regression task as a sequence prediction
process. In this way, we decompose an ordinal regression task into a series of
recursive binary classification steps, so as to subtly distinguish adjacent
categories. Comprehensive experiments show the effectiveness of distinguishing
adjacent categories for performance improvement and our new approach exceeds
state-of-the-art performances in four different scenarios. Codes are available
at https://github.com/wjh892521292/Ord2Seq.
Related papers
- dlordinal: a Python package for deep ordinal classification [3.420642569478584]
dlordinal is a new Python library that unifies many recent deep ordinal classification methodologies.
It implements the top performing state-of-the-art deep learning techniques for ordinal classification problems.
arXiv Detail & Related papers (2024-07-24T11:07:20Z) - Deep Imbalanced Regression via Hierarchical Classification Adjustment [50.19438850112964]
Regression tasks in computer vision are often formulated into classification by quantizing the target space into classes.
The majority of training samples lie in a head range of target values, while a minority of samples span a usually larger tail range.
We propose to construct hierarchical classifiers for solving imbalanced regression tasks.
Our novel hierarchical classification adjustment (HCA) for imbalanced regression shows superior results on three diverse tasks.
arXiv Detail & Related papers (2023-10-26T04:54:39Z) - Regularization-Based Methods for Ordinal Quantification [49.606912965922504]
We study the ordinal case, i.e., the case in which a total order is defined on the set of n>2 classes.
We propose a novel class of regularized OQ algorithms, which outperforms existing algorithms in our experiments.
arXiv Detail & Related papers (2023-10-13T16:04:06Z) - Learning-to-Rank Meets Language: Boosting Language-Driven Ordering
Alignment for Ordinal Classification [60.28913031192201]
We present a novel language-driven ordering alignment method for ordinal classification.
Recent developments in pre-trained vision-language models inspire us to leverage the rich ordinal priors in human language.
Experiments on three ordinal classification tasks, including facial age estimation, historical color image (HCI) classification, and aesthetic assessment demonstrate its promising performance.
arXiv Detail & Related papers (2023-06-24T04:11:31Z) - Parametric Classification for Generalized Category Discovery: A Baseline
Study [70.73212959385387]
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples.
We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem.
We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
arXiv Detail & Related papers (2022-11-21T18:47:11Z) - Set-valued prediction in hierarchical classification with constrained
representation complexity [4.258263831866309]
We focus on hierarchical multi-class classification problems, where valid sets correspond to internal nodes of the hierarchy.
We propose three methods and evaluate them on benchmark datasets.
arXiv Detail & Related papers (2022-03-13T15:13:19Z) - Universally Rank Consistent Ordinal Regression in Neural Networks [4.462334751640166]
Recent methods have resorted to converting ordinal regression into a series of extended binary classification subtasks.
Here we demonstrate that the subtask probabilities form a Markov chain.
We show how to straightforwardly modify neural network architectures to exploit this fact and thereby constrain predictions to be universally rank consistent.
arXiv Detail & Related papers (2021-10-14T15:44:08Z) - Semi-supervised sequence classification through change point detection [22.14406516031776]
We propose a novel framework for semi-supervised learning in such contexts.
In an unsupervised manner, change point detection methods can be used to identify points within a sequence corresponding to likely class changes.
We show that change points provide examples of similar/dissimilar pairs of sequences which, when coupled with labeled, can be used in a semi-supervised classification setting.
arXiv Detail & Related papers (2020-09-24T17:23:13Z) - Exploring the Hierarchy in Relation Labels for Scene Graph Generation [75.88758055269948]
The proposed method can improve several state-of-the-art baselines by a large margin (up to $33%$ relative gain) in terms of Recall@50.
Experiments show that the proposed simple yet effective method can improve several state-of-the-art baselines by a large margin.
arXiv Detail & Related papers (2020-09-12T17:36:53Z) - Convolutional Ordinal Regression Forest for Image Ordinal Estimation [52.67784321853814]
We propose a novel ordinal regression approach, termed Convolutional Ordinal Regression Forest or CORF, for image ordinal estimation.
The proposed CORF integrates ordinal regression and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships.
The effectiveness of the proposed CORF is verified on two image ordinal estimation tasks, showing significant improvements and better stability over the state-of-the-art ordinal regression methods.
arXiv Detail & Related papers (2020-08-07T10:41:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.