SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.02187 · ICML · 2023

CLUSTSEG: Clustering for Universal Segmentation

Wenguan Wang, James Liang, Dongfang Liu, Tianfei Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present CLUSTSEG, a general, transformerbased framework that tackles different image segmentation tasks (i.e., superpixel, semantic, instance, and panoptic) through a unified, neural clustering scheme. Regarding queries as cluster centers, CLUSTSEG is innovative in two aspects:xcluster centers are initialized in heterogeneous ways so as to pointedly address task-specific demands (e.g., instance-or category-level distinctiveness), yet without modifying the architecture; and y pixelcluster assignment, formalized in a cross-attention fashion, is alternated with cluster center update, yet without learning additional parameters. These innovations closely link CLUSTSEG to EM clustering and make it a transparent and powerful framework that yields superior results across the above segmentation tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.02187")
get_code_for_paper("2305.02187")
have("2305.02187")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.02187.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.02187.svg)](https://syntology.ai/paper/2305.02187)

Connect an agent — have() is free.