# Orderless Recurrent Models for Multi-label Classification

Source: [Orderless Recurrent Models for Multi-label Classification](<https://www.sota2.com/research/paper/68fa67381e209131cea14fa7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:09:20.078Z

Authors: Vacit Oguz Yazici, Abel Gonzalez-Garcia, Arnau Ramisa, Bartlomiej Twardowski, Joost van de Weijer

Published: 2019-11-22T12:25:14.000Z

## Abstract

Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g.\\ first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-label recognition on MS-COCO (val)](<https://www.sota2.com/research/sota/multi-label-recognition-on-ms-coco-val.md>): Multi-label recognition; MS-COCO (val); F1 Score (All): 81.5.

- [Multi-label Image Classification on MS-COCO 2014 (test)](<https://www.sota2.com/research/sota/multi-label-image-classification-on-ms-coco-2014-test.md>): Multi-label Image Classification; MS-COCO 2014 (test); F1 Score (Top-3): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.09996>)

[PDF](<https://arxiv.org/pdf/1911.09996.pdf>)