Key Patch Proposer: Key Patches Contain Rich Information
Keywords: masked autoencoder, active learning, submodular function
TL;DR: This paper introduces a potential method for active learning utilizing Masked Auto-encoder.
Abstract: In this paper, we introduce a novel algorithm named Key Patch Proposer (KPP) designed to select key patches in an image without additional training. Our experiments showcase KPP's robust capacity to capture semantic information by both reconstruction and classification tasks. The efficacy of KPP suggests its potential application in active learning for semantic segmentation. Our source code is publicly available at https://github.com/CA-TT-AC/key-patch-proposer.
Submission Number: 35
Loading