G2Net: Generic Game-Theoretic Network for Partial-Label Image Classification

Rabab Abdelfattah (University of South Carolina),* Xin Zhang (university of south carolina), Mostafa M. Fouda (Idaho State University), XIAOFENG Wang (University of South Carolina), Song Wang (University of South Carolina)
The 33rd British Machine Vision Conference


Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, since it could be expensive in practice to annotate all the labels in every training image. Existing works on partial-label learning focus on the case where each training image is labeled with only a subset of its positive/negative labels. To effectively address partial-label classification, this paper proposes an end-to-end Generic Game-theoretic Network (G2Net) for partial-label learning, which can be applied to most partial label settings, including a very challenging, but annotation-efficient case where only a subset of the training images are labeled, each with only one positive label, while the rest of the training images remain unlabeled. In G2Net, each unobserved label is associated with a soft pseudo label, which, together with the network, formulates a two-player non-zero non-cooperative game. The objective of the network is to minimize the loss function with given pseudo labels, while the pseudo labels will seek convergence to 1 (positive) or 0 (negative) with a penalty of deviating from the predicted labels determined by the network. In addition, we introduce a confidence-aware scheduler into the loss of the network to adaptively perform easy-to-hard learning for different labels. Extensive experiments demonstrate that our proposed G2Net outperforms many state-of-the-art multi-label classification methods under various partial label settings on four different datasets.



author    = {Rabab Abdelfattah and Xin Zhang and Mostafa M. Fouda and XIAOFENG Wang and Song Wang},
title     = {G2Net: Generic Game-Theoretic Network for Partial-Label Image Classification},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year      = {2022},
url       = {https://bmvc2022.mpi-inf.mpg.de/0309.pdf}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection