loading page

MIL-Mixer: A Robust Bag Encoding Strategy for Multiple Instance Learning (MIL) using MLP-Mixer
  • +2
  • Muhammad Waqas ,
  • Zeshan Khan,
  • Syed Umaid,
  • Muhammad Atif Tahir,
  • Asif Raza
Muhammad Waqas
FAST School of Computing, National University of Computer and Emerging Sciences (FAST-NUCES)

Corresponding Author:[email protected]

Author Profile
Zeshan Khan
FAST School of Computing, National University of Computer and Emerging Sciences (FAST-NUCES)
Syed Umaid
FAST School of Computing, National University of Computer and Emerging Sciences (FAST-NUCES)
Muhammad Atif Tahir
FAST School of Computing, National University of Computer and Emerging Sciences (FAST-NUCES)
Asif Raza
Department of Computer Science, Bahauddin Zakariya University

Abstract

This paper presents a robust bag encoding strategy based on an MLP mixer. The proposed approach introduces the mixing concept to MIL applications, which helps to generate robust bag encoding. The existing bag encoding strategies for MIL applications consider instances in the bag as independent. This assumption may restrict the performance of these algorithms. Therefore, this paper proposes MIL-Mixer, which utilizes the information between the instances to generate a robust bag encoding. We also extend MLP-Mixture to use classification token similar to vision transformers which diversify the encoding generation process. In this study, three benchmark MIL datasets are used to assess the performance of the proposed MIL-Mixer. In comparison with existing MIL approaches, the proposed MIL-Mixer achieves better performance.
22 Jan 2024Submitted to TechRxiv
26 Jan 2024Published in TechRxiv