# Key Patch Proposer: Key Patches Contain Rich Information

Source: [Key Patch Proposer: Key Patches Contain Rich Information](<https://www.sota2.com/research/paper/68fa723a1e209131cea55183>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:30:07.638Z

Authors: Jing Xu, Beiwen Tian, Hao Zhao

Published: 2024-02-18T04:59:23.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.11458>)

[PDF](<https://arxiv.org/pdf/2402.11458.pdf>)