paper-with-me

홈 › Papers

Attribute Attention for Semantic Disambiguation in Zero-Shot Learning

2019-10-01 · ICCV 2019 10 · Yang Liu, Jishun Guo, Deng Cai, Xiaofei He

Zero-shot learning (ZSL) aims to accurately recognize unseen objects by learning mapping matrices that bridge the gap between visual information and semantic attributes. Previous works implicitly treat attributes equally in compatibility score while ignoring that they have different importance for discrimination, which leads to severe semantic ambiguity. Considering both low-level visual information and global class-level features that relate to this ambiguity, we propose a practical Latent Feature Guided Attribute Attention (LFGAA) framework to perform object-based attribute attention for semantic disambiguation. By distracting semantic activation in dimensions that cause ambiguity, our method outperforms existing state-of-the-art methods on AwA2, CUB and SUN datasets in both inductive and transductive settings.

📄 PDF Abstract BibTeX

Code (1)

ZJULearning/AttentionZSL 공식 구현 pytorch

Tasks

AttributeZero-Shot Learning

Similar Papers 제목 키워드 기반

Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels

2026-04-20 · Jiangnan Li, Linqing Huang, Xiaowen Yan, Min Gan 외 arxiv

Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To …

Zero-Shot Learning

Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning

2023-03-27 · CVPR 2023 1 · Man Liu, Feng Li, Chunjie Zhang, Yunchao Wei 외

Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information. Prior works mainly localize…

AttributeDecoderGeneralized Zero-Shot LearningZero-Shot Learning

Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation

2023-05-22 · CVPR 2023 1 · Shuting He, Henghui Ding, Wei Jiang

Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends t…

Instance SegmentationSegmentationSemantic SegmentationZero-Shot Instance Segmentation

Dual Relation Mining Network for Zero-Shot Learning

2024-05-06 · Jinwei Han, Yingguo Gao, Zhiwen Lin, Ke Yan 외

Zero-shot learning (ZSL) aims to recognize novel classes through transferring shared semantic knowledge (e.g., attributes) from seen classes to unseen classes. Recently, attention-based methods have exhibited significant…

AttributeRelationTransfer LearningZero-Shot Learning

MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning

2022-03-07 · CVPR 2022 1 · Shiming Chen, Ziming Hong, Guo-Sen Xie, Wenhan Yang 외

The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable knowledge transfer to unseen classes. Prio…

AttributeTransfer LearningZero-Shot Learning