paper-with-me

Papers

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers

2023-06-03 · CVPR 2023 1 · Chenyang Lu, Daan de Geus, Gijs Dubbelman

This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs). Existing works have proposed token reduction approaches to improve the efficiency of ViT-based image classification networks, but these methods are not directly applicable to semantic segmentation, which we address in this work. We observe that, for semantic segmentation, multiple image patches can share a token if they contain the same semantic class, as they contain redundant information. Our approach leverages this by employing an efficient, class-agnostic policy network that predicts if image patches contain the same semantic class, and lets them share a token if they do. With experiments, we explore the critical design choices of CTS and show its effectiveness on the ADE20K, Pascal Context and Cityscapes datasets, various ViT backbones, and different segmentation decoders. With Content-aware Token Sharing, we are able to reduce the number of processed tokens by up to 44%, without diminishing the segmentation quality.

📄 PDF Abstract BibTeX arXiv:2306.02095

Code (1)

tue-mps/cts-segmenter 공식 구현 pytorch

Tasks

Computational Efficiencyimage-classificationImage ClassificationSegmentationSemantic SegmentationToken Reduction

Similar Papers 제목 키워드 기반

Native Segmentation Vision Transformers

2025-05-22 · Guillem Brasó, Aljoša Ošep, Laura Leal-Taixé

Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically…

Segmentation

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching

2025-09-29 · Xinye Zhao, Spyridon Mastorakis arxiv

As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a…

Multi-Document Summarization

DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion

2023-09-21 · Zhenzhen Chu, Jiayu Chen, Cen Chen, Chengyu Wang 외

Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the …

image-classificationImage Classificationobject-detectionObject Detection+2

An Image Patch is a Wave: Phase-Aware Vision MLP

2021-11-24 · CVPR 2022 1 · Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu 외

In the field of computer vision, recent works show that a pure MLP architecture mainly stacked by fully-connected layers can achieve competing performance with CNN and transformer. An input image of vision MLP is usually…

image-classificationImage Classificationobject-detectionObject Detection+1

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization

2025-07-13 · Son Nguyen, Giang Nguyen, Hung Dao, Thao Do 외 arxiv

Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spatial structure. Yet existing multimodal l…

Key Information Extraction