Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction

TL;DR

Ord2Seq introduces a novel sequence prediction framework for ordinal regression that transforms ordinal labels into label sequences, enabling better distinction of adjacent categories and achieving state-of-the-art results across multiple scenarios.

Contribution

This paper presents the first sequence prediction approach for ordinal regression, improving the distinction of adjacent categories and surpassing existing methods.

Findings

Outperforms state-of-the-art methods in four scenarios

Effectively distinguishes adjacent categories

Transforms ordinal regression into sequence prediction

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.