arrow
返回

Generative Multi-Label Zero-Shot Learning

delete2023-01-01
delete0
delete
OA
AI
A
Akshita Gupta
S
Sanath Narayan
S
Salman Khan
F
Fahad Shahbaz Khan
Ling Shao 封面图
Ling Shao (Ling Shao)
J
Joost van de Weijer
DOI:10.1109/tpami.2023.3295772delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods.
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Pattern Analysis and Machine Intelligence 封面图
IEEE Transactions on Pattern Analysis and Machine Intelligence
IF:
18.6
论文数:
2.9K
被引数:
10.9W

机构

M
Mohamed bin Zayed University of Artificial Intelligence
学者数:
146
论文数: 106
被引数: 107
U
University of Guelph
学者数:
813
论文数: 374
被引数: 8.2K
A
Australian National University
学者数:
1.5K
论文数: 741
被引数: 2.0W
U
Universitat Autonoma de Barcelona
学者数:
728
论文数: 308
被引数: 446
中国科学院大学 封面图
中国科学院大学
学者数:
2.5K
论文数: 999
被引数: 1.3K
T
technology innovation institute
学者数:
61
论文数: 41
被引数: 684
学者 查看更多机构
引用论文

引用论文

Emerging Properties in Self-Supervised Vision Transformers自监督视觉变换器中的新兴特性
err2021-10-01
err0
errOAAI
errMathilde Caron; Hugo Touvron; Ishan Misra; Herve Jegou; Julien Mairal; Piotr Bojanowski; Armand Joulin
err分享
err收藏
err分享
err收藏
err分享
err收藏
Multi-modal Cycle-Consistent Generalized Zero-Shot Learning
err2018-10-06
err0
PREAI
errRafael Felix; B. G. Vijay Kumar; Ian Reid; Gustavo Carneiro
err分享
err收藏
NUS-WIDE
err2009-07-08
err0
PREAI
errTat-Seng Chua; Jinhui Tang; Richang Hong; Haojie Li; Zhiping Luo; Yantao Zheng
err分享
err收藏
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
err2020-11-17
err0
PREAI
errSanath Narayan; Akshita Gupta; Fahad Shahbaz Khan; Cees G. M. Snoek; Ling Shao
err分享
err收藏
err分享
err收藏
Deep Ranking for Image Zero-Shot Multi-Label Classification图像零拍多标签分类的深度排序
err2020-01-01
err36
PREAI
errJi, Zhong; Cui, Biying; Li, Huihui; Jiang, Yu-Gang; Xiang, Tao; Hospedales, Timothy; Fu, Yanwei
err分享
err收藏
学者 查看更多内容