From Weakly Supervised Learning to Biquality Learning: an Introduction

Abstract

The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies". In WSL use cases, a variety of situations exists where the collected "information" is imperfect. The paradigm of WSL attempts to list and cover these problems with associated solutions. In this paper, we review the research progress on WSL with the aim to make it as a brief introduction to this field. We present the three axis of WSL cube and an overview of most of all the elements of their facets. We propose three measurable quantities that acts as coordinates in the previously defined cube namely: Quality, Adaptability and Quantity of information. Thus we suggest that Biquality Learning framework can be defined as a plan of the WSL cube and propose to re-discover previously unrelated patches in WSL literature as a unified Biquality Learning literature.

Multi-Label Image Classification with Weak Correlation Prior

“…T T * T T As we know, when updating , Formula (7) can be simplified to Formula (8). Assume and are the optimal solution obtained by updating in the previous and current iterations.…”

“…WS-MLIC with incomplete supervision is designed to process images with incomplete label matrix information [18,19] . For example, Cabral et al [8] considered the case that class assignments of training examples are incomplete and propose a low-rank matrix completion framework to tackle this challenge. Although the above three types of WS-MLIC methods greatly reduce the requirement for the label matrix, they still require a certain number of labeled images to assist in training in order to assign multiple labels to unknown images.…”