# From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation

Source: [From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation](<https://www.sota2.com/research/paper/68fa6ba51e209131cea2f890>)

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

Data updated: 2025-10-25T23:54:05.632Z

Authors: Zhangxuan Gu, Siyuan Zhou, Li Niu, Zihan Zhao, Liqing Zhang

Published: 2020-09-25T13:26:30.000Z

## Abstract

Zero-shot learning has been actively studied for image classification task to relieve the burden of annotating image labels. Interestingly, semantic segmentation task requires more labor-intensive pixel-wise annotation, but zero-shot semantic segmentation has only attracted limited research interest. Thus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories. In this paper, we propose a novel Context-aware feature Generation Network (CaGNet), which can synthesize context-aware pixel-wise visual features for unseen categories based on category-level semantic representations and pixel-wise contextual information. The synthesized features are used to finetune the classifier to enable segmenting unseen objects. Furthermore, we extend pixel-wise feature generation and finetuning to patch-wise feature generation and finetuning, which additionally considers inter-pixel relationship. Experimental results on Pascal-VOC, Pascal-Context, and COCO-stuff show that our method significantly outperforms the existing zero-shot semantic segmentation methods. Code is available at https://github.com/bcmi/CaGNetv2-Zero-Shot-Semantic-Segmentation.

## 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/2009.12232>)

[PDF](<https://arxiv.org/pdf/2009.12232.pdf>)