# SGC-VQGAN: Towards Complex Scene Representation via Semantic Guided Clustering Codebook

Source: [SGC-VQGAN: Towards Complex Scene Representation via Semantic Guided Clustering Codebook](<https://www.sota2.com/research/paper/68fa74c01e209131cea637ff>)

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

Data updated: 2025-10-26T03:17:28.990Z

Authors: Chenjing Ding, Chiyu Wang, Boshi Liu, Xi Guo, Weixuan Tang, Wei Wu

Published: 2024-09-09T23:12:43.000Z

## Abstract

Vector quantization (VQ) is a method for deterministically learning features through discrete codebook representations. Recent works have utilized visual tokenizers to discretize visual regions for self-supervised representation learning. However, a notable limitation of these tokenizers is lack of semantics, as they are derived solely from the pretext task of reconstructing raw image pixels in an auto-encoder paradigm. Additionally, issues like imbalanced codebook distribution and codebook collapse can adversely impact performance due to inefficient codebook utilization. To address these challenges, We introduce SGC-VQGAN through Semantic Online Clustering method to enhance token semantics through Consistent Semantic Learning. Utilizing inference results from segmentation model , our approach constructs a temporospatially consistent semantic codebook, addressing issues of codebook collapse and imbalanced token semantics. Our proposed Pyramid Feature Learning pipeline integrates multi-level features to capture both image details and semantics simultaneously. As a result, SGC-VQGAN achieves SOTA performance in both reconstruction quality and various downstream tasks. Its simplicity, requiring no additional parameter learning, enables its direct application in downstream tasks, presenting significant potential.

## 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/2409.06105>)

[PDF](<https://arxiv.org/pdf/2409.06105.pdf>)
