G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification

by   Rabab Abdelfattah, et al.

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 (G2NetPL) 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 G2NetPL, each unobserved label is associated with a soft pseudo label, which, together with the network, formulates a two-player non-zero-sum 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 G2NetPL outperforms many state-of-the-art multi-label classification methods under various partial-label settings on three different datasets.


page 1

page 4

page 9

page 10


PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification

Multi-label image classification aims to predict all possible labels in ...

Acknowledging the Unknown for Multi-label Learning with Single Positive Labels

Due to the difficulty of collecting exhaustive multi-label annotations, ...

Pseudo Labels for Single Positive Multi-Label Learning

The cost of data annotation is a substantial impediment for multi-label ...

Positive Label Is All You Need for Multi-Label Classification

Multi-label classification (MLC) suffers from the inevitable label noise...

Asymmetric Loss For Multi-Label Classification

Pictures of everyday life are inherently multi-label in nature. Hence, m...

Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

As a promising solution of reducing annotation cost, training multi-labe...

A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation

In this paper, we study the partial multi-label (PML) image classificati...

Please sign up or login with your details

Forgot password? Click here to reset