Skip to main navigation Skip to search Skip to main content

Clustering-Based Adaptive Query Generation for Semantic Segmentation

  • Konkuk University

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

Semantic segmentation is one of the crucial tasks in the field of computer vision, aiming to label each pixel according to its class. Most recently, several semantic segmentation methods, which adopt the transformer decoder with learnable queries, have achieved the impressive improvement. However, since learnable queries are primarily determined by the distribution of training samples, discriminative characteristics of the input image often have been disregarded. In this letter, we propose a novel clustering-based query generation method for semantic segmentation. The key idea of the proposed method is to adaptively generate queries based on the clustering scheme, which leverages semantic affinities in the latent space. By aggregating latent features that represent the same class in a given input, the semantic information of each class can be efficiently encoded into the query. Furthermore, we propose to apply the auxiliary loss function to predict the segmentation result in a coarse scale during the process of query generation. This enables each query to grasp spatial information of the target object in a given image. Experimental results on various benchmarks show that the proposed method effectively improves the performance of semantic segmentation.

Original languageEnglish
Pages (from-to)1580-1584
Number of pages5
JournalIEEE Signal Processing Letters
Volume32
DOIs
StatePublished - 2025

Keywords

  • clustering-based adaptive query generation
  • deep learning
  • learnable queries
  • Semantic segmentation

Fingerprint

Dive into the research topics of 'Clustering-Based Adaptive Query Generation for Semantic Segmentation'. Together they form a unique fingerprint.

Cite this