Learning unbiased zero-shot semantic segmentation networks via transductive transfer

2020-07-01 · Haiyang Liu, Yichen Wang, Jiayi Zhao, Guowu Yang, Fengmao Lv

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.

📄 PDF Abstract BibTeX arXiv:2007.00515

Code (1)

ycccccccccc/Learning-unbiased-zero-shot-semantic-segmentation-networks-via-transductive-transfer pytorch

Tasks

AttributePrediction Segmentation Semantic Segmentation Transfer Learning Zero-Shot Learning Zero-Shot Semantic Segmentation

Transductive Unbiased Embedding for Zero-Shot Learning

2018-03-30 · CVPR 2018 6 · Jie Song, Chengchao Shen, Yezhou Yang, Yang Liu 외

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after …

Transductive Learning Zero-Shot Learning

Exploiting Semantic Attributes for Transductive Zero-Shot Learning

2023-03-17 · Zhengbo Wang, Jian Liang, Zilei Wang, Tieniu Tan

Zero-shot learning (ZSL) aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. A recent paradigm called transductive zero-shot learni…

Attribute Decoder Generative Adversarial Network Zero-Shot Learning

ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation

2022-12-07 · CVPR 2023 1 · Ziqin Zhou, BoWen Zhang, Yinjie Lei, Lingqiao Liu 외

Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. The general idea is to first generate class-agnostic region proposals and then feed the cropped proposal regions to CLIP to …

Semantic Segmentation zero-shot-classification Zero-Shot Learning Zero-Shot Semantic Segmentation

Transductive Multi-view Zero-Shot Learning

2015-01-19 · Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong

Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no ann…

Transfer Learning Zero-Shot Learning

Transductive Multi-class and Multi-label Zero-shot Learning

2015-03-26 · Yanwei Fu, Yongxin Yang, Timothy M. Hospedales, Tao Xiang 외

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed t…

Multi-label zero-shot learning Transductive Learning Transfer Learning Zero-Shot Learning