# Learning unbiased zero-shot semantic segmentation networks via transductive transfer

arXiv: https://arxiv.org/abs/2007.00515 · HTML: https://mlsanity.com/paper/2007.00515/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [A Closer Look at Self-training for Zero-Label Semantic Segmentation](https://mlsanity.com/paper/2104.11692/) (2021)
- [Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation](https://mlsanity.com/paper/2306.11087/) (2023)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Delving into Shape-aware Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2304.08491/) (2023)
- [Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2305.13173/) (2023)
- [Conterfactual Generative Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2106.06360/) (2021)
- [Zero-shot point cloud segmentation by transferring geometric primitives](https://mlsanity.com/paper/2210.09923/) (2022)
- [Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding](https://mlsanity.com/paper/2111.15181/) (2021)
- [Orthogonal-Coding-Based Feature Generation for Transductive Open-Set Recognition via Dual-Space Consistent Sampling](https://mlsanity.com/paper/2207.05957/) (2022)
- [Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2301.07336/) (2023)

## Abstract (arXiv)

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear. Since it is impractical to collect labeled data for all categories, how to conduct zero-shot learning in semantic segmentation establishes an important problem. Although the attribute embedding of categories can promote effective knowledge transfer across different categories, the prediction of segmentation network reveals obvious bias to seen categories. In this paper, we propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation. Our method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training. To be specific, the source images are used to learn the relationship between visual images and semantic embeddings, while the target images are used to alleviate the prediction bias towards seen categories. We conduct comprehensive experiments on diverse split s of the PASCAL dataset. The experimental results clearly demonstrate the effectiveness of our method.