paper-with-me

홈 › Papers

Attribute Localization and Revision Network for Zero-Shot Learning

2023-10-11 · Junzhe Xu, Suling Duan, Chenwei Tang, Zhenan He, Jiancheng Lv

Zero-shot learning enables the model to recognize unseen categories with the aid of auxiliary semantic information such as attributes. Current works proposed to detect attributes from local image regions and align extracted features with class-level semantics. In this paper, we find that the choice between local and global features is not a zero-sum game, global features can also contribute to the understanding of attributes. In addition, aligning attribute features with class-level semantics ignores potential intra-class attribute variation. To mitigate these disadvantages, we present Attribute Localization and Revision Network in this paper. First, we design Attribute Localization Module (ALM) to capture both local and global features from image regions, a novel module called Scale Control Unit is incorporated to fuse global and local representations. Second, we propose Attribute Revision Module (ARM), which generates image-level semantics by revising the ground-truth value of each attribute, compensating for performance degradation caused by ignoring intra-class variation. Finally, the output of ALM will be aligned with revised semantics produced by ARM to achieve the training process. Comprehensive experimental results on three widely used benchmarks demonstrate the effectiveness of our model in the zero-shot prediction task.

📄 PDF Abstract BibTeX arXiv:2310.07548

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeZero-Shot Learning

Methods 이 논문이 사용한 방법론

PatchGAN 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Revision Network Revision Network is a style transfer module that aims to revise the rough stylized image via generating residual details image $r_{c s}$, while the final stylized image is…

Similar Papers 제목 키워드 기반

Attribute Prototype Network for Zero-Shot Learning

2020-08-19 · NeurIPS 2020 12 · Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele 외

From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image …

AttributeRepresentation LearningZero-Shot Learning

Attribute Prototype Network for Any-Shot Learning

2022-04-04 · Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele 외

Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot…

AttributeFew-Shot Image ClassificationGZSL Video Classificationimage-classification+3

Simple and effective localized attribute representations for zero-shot learning

2020-06-10 · Shiqi Yang, Kai Wang, Luis Herranz, Joost Van de Weijer

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features togethe…

AttributeZero-Shot Learning

On Implicit Attribute Localization for Generalized Zero-Shot Learning

2021-03-08 · Shiqi Yang, Kai Wang, Luis Herranz, Joost Van de Weijer

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, ma…

AttributeGeneralized Zero-Shot LearningZero-Shot Learning

Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions

2017-07-28 · ICCV 2017 10 · Pascal Mettes, Cees G. M. Snoek

We aim for zero-shot localization and classification of human actions in video. Where traditional approaches rely on global attribute or object classification scores for their zero-shot knowledge transfer, our main contr…

Action LocalizationAttributeClassificationGeneral Classification+3