Unlocking the Potential of Pre-Trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

Ziqin Zhou, Hai-Ming Xu, Yangyang Shu, Lingqiao Liu
2/9/2026

No official code found. Best implementation: ZiqinZhou66/FewSegwithRD (5 stars, MIT, last commit 2024-03-26).

DOISemantic Scholar

Code Implementations(1)

ZiqinZhou66/FewSegwithRDCommunity72%
MIT

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

50Mar 26, 20242 years agoMIT

Similar Papers

Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction

92% match2026

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

92% match2026

Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms

92% match1 repo32026

CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling

91% match1 repo42026

JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models

91% match1 repo72026

Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning

91% match2026

Cite this paper

@article{zhou2026unlocking,
  title  = {Unlocking the Potential of Pre-Trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors},
  author = {Ziqin Zhou and Hai-Ming Xu and Yangyang Shu and Lingqiao Liu},
  year   = {2026},
  doi    = {10.1109/CVPR52733.2024.00366},
  url    = {https://doi.org/10.1109/CVPR52733.2024.00366},
  journal = {CVPR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/3ad2ba8eca619fe2a45f41271f3624b2f5a3e8f5.svg)](https://codeofpaper.com/paper/3ad2ba8eca619fe2a45f41271f3624b2f5a3e8f5)

Discussion