# Fuse Local and Global Semantics in Representation Learning

Source: [Fuse Local and Global Semantics in Representation Learning](<https://www.sota2.com/research/paper/68fa6bde1e209131cea30b88>)

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

Data updated: 2025-10-25T23:59:05.045Z

Authors: Yuchi Zhao, Yuhao Zhou

Published: 2022-02-28T14:48:51.000Z

## Abstract

We propose Fuse Local and Global Semantics in Representation Learning (FLAGS) to generate richer representations. FLAGS aims at extract both global and local semantics from images to benefit various downstream tasks. It shows promising results under common linear evaluation protocol. We also conduct detection and segmentation on PASCAL VOC and COCO to show the representations extracted by FLAGS are transferable.

## 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/2202.13837>)

[PDF](<https://arxiv.org/pdf/2202.13837.pdf>)