Filters








5,900 Hits in 7.3 sec

Semantic Diversity Learning for Zero-Shot Multi-label Classification [article]

Avi Ben-Cohen, Nadav Zamir, Emanuel Ben Baruch, Itamar Friedman, Lihi Zelnik-Manor
2021
This study introduces an end-to-end model training for multi-label zero-shot learning that supports semantic diversity of the images and labels.  ...  Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse  ...  Semantic Diversity Learning In this section, we present our proposed method for training multi-label zero-shot models.  ... 
doi:10.48550/arxiv.2105.05926 fatcat:763hq6jm7va2zbckrirl4rkiey

Learning Structured Semantic Embeddings for Visual Recognition [article]

Dong Li, Hsin-Ying Lee, Jia-Bin Huang, Shengjin Wang, Ming-Hsuan Yang
2017 arXiv   pre-print
Extensive evaluations demonstrate the effectiveness of the proposed structured embeddings for single-label classification, multi-label classification, and zero-shot recognition.  ...  In this paper, we propose the structured discriminative and difference constraints to learn visual-semantic embeddings.  ...  , multi-label classification, and zero-shot recognition.  ... 
arXiv:1706.01237v1 fatcat:fdsvdt2ijjawpludyjyfjt6ucy

Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention [article]

Ziming Liu, Song Guo, Jingcai Guo, Yuanyuan Xu, Fushuo Huo
2022 arXiv   pre-print
Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample.  ...  In this paper, we propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions to calibrate the training process of the classifier.  ...  multi-label zero-shot learning method.  ... 
arXiv:2203.03483v1 fatcat:v4oa6y4qgbbk5pgtl5bfc2joy4

Semantic-Guided Multi-Attention Localization for Zero-Shot Learning [article]

Yizhe Zhu and Jianwen Xie and Zhiqiang Tang and Xi Peng and Ahmed Elgammal
2019 arXiv   pre-print
Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes.  ...  We propose a semantic-guided multi-attention localization model, which automatically discovers the most discriminative parts of objects for zero-shot learning without any human annotations.  ...  In the zero-shot learning scenario, embedding softmax loss [13, 19] is used by embedding the class semantic representations into a multi-class classification framework.  ... 
arXiv:1903.00502v2 fatcat:6ry72mee3fg4rm26waanacp5pq

A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning

Dat Huynh, Ehsan Elhamifar
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work, we develop a shared multi-attention model for multi-label zero-shot learning.  ...  Finally, we learn a compatibility function to distinguish labels based on the selected attention.  ...  -Clustering labels based on semantic vectors and learning Table 2 : 2 Ablation study for multi-label zero-shot (ZS) and multi- label generalized zero-shot (GZS) performance on NUS-WIDE.  ... 
doi:10.1109/cvpr42600.2020.00880 dblp:conf/cvpr/HuynhE20a fatcat:yy6ce7cm6vbibpgk4rwcefnrgy

Unified Semantic Typing with Meaningful Label Inference [article]

James Y. Huang, Bangzheng Li, Jiashu Xu, Muhao Chen
2022 arXiv   pre-print
In this paper, we present UniST, a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space.  ...  Our experiments demonstrate that UniST achieves strong performance across three semantic typing tasks: entity typing, relation classification and event typing.  ...  Acknowledgment We appreciate the anonymous reviewers for their insightful comments and suggestions. This material is supported in part by the DARPA MCS program under Contract No.  ... 
arXiv:2205.01826v1 fatcat:mc3ck4e4dvhudamcx3eyt55r2u

Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning [article]

Yi Zhang and Sheng Huang and Xi Peng and Dan Yang
2021 arXiv   pre-print
Data augmentation is a powerful technique for improving the performance of the few-shot classification task.  ...  It generates more samples as supplements, and then this task can be transformed into a common supervised learning issue for solution.  ...  the semantic and visual information as multi-modal conditions to generate the features for few-shot learning.  ... 
arXiv:2106.14467v1 fatcat:r47ii7hhzrhb3jqitd5dmq2ocy

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

Thomas Mensink, Efstratios Gavves, Cees G.M. Snoek
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
We also show that our zero-shot classifiers can serve as priors for few-shot learning.  ...  We conclude that cooccurrence statistics suffice for zero-shot classification.  ...  To the best of our knowledge, we are the first to present a model for multi-label zero-shot classification.  ... 
doi:10.1109/cvpr.2014.313 dblp:conf/cvpr/MensinkGS14 fatcat:56qfokkb65gl3gicomfayxkcnq

Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection [article]

Hoang Nguyen, Chenwei Zhang, Congying Xia, Philip S. Yu
2020 arXiv   pre-print
These limitations inhibit generalizing capability towards Generalized Few-shot Learning settings where both seen and novel classes are co-existent.  ...  We also propose a more challenging evaluation setting that considers classification on the joint all-class label space. Extensive experimental results demonstrate the effectiveness of our method.  ...  Acknowledgments We thank you reviewers for insightful feedback. This work is supported in part by NSF under grants III-1763325, III-1909323, and SaTC-1930941.  ... 
arXiv:2010.02481v2 fatcat:2a6ie3nmwbajbienz5v6g2riwq

Reconstructing Capsule Networks for Zero-shot Intent Classification

Han Liu, Xiaotong Zhang, Lu Fan, Xuandi Fu, Qimai Li, Xiao-Ming Wu, Albert Y.S. Lam
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
A recently proposed zero-shot intent classification method, IntentCapsNet, has been shown to achieve state-of-the-art performance.  ...  However, it has two unaddressed limitations: (1) it cannot deal with polysemy when extracting semantic capsules; (2) it hardly recognizes the utterances of unseen intents in the generalized zero-shot intent  ...  Acknowledgments We would like to thank the anonymous reviewers for their helpful comments towards improving the manuscript. This research was supported by the grant HK ITF UIM/377.  ... 
doi:10.18653/v1/d19-1486 dblp:conf/emnlp/LiuZFFLWL19 fatcat:jxfxdsjkmnhjziz3vohqn67cri

Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data [article]

Kun Liu, Wu Liu, Huadong Ma, Wenbing Huang, Xiongxiong Dong
2017 arXiv   pre-print
Zero-shot learning is potential to be applied to solve these issues since it can perform classification without positive example.  ...  Our experimental results demonstrate that, under the generalize setting, typical zero-shot learning methods are no longer effective for the dataset we applied.  ...  The dataset is dirty due Table 2 Classification accuracies (%) on classic zero-shot learning (A U → U ), multi-class classification for seen classes (A S → S), and generalized zero-shot learning (A  ... 
arXiv:1710.07455v1 fatcat:datwl63c5jd2hiylkz7636lra4

MetaICL: Learning to Learn In Context [article]

Sewon Min, Mike Lewis, Luke Zettlemoyer, Hannaneh Hajishirzi
2022 arXiv   pre-print
MetaICL outperforms a range of baselines including in-context learning without meta-training and multi-task learning followed by zero-shot transfer.  ...  We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of  ...  Acknowledgements We thank Ari Holtzman and Victoria Lin for comments and discussions, and Tim Dettmers for help with experiments.  ... 
arXiv:2110.15943v2 fatcat:jgdtfix5xrcmvbzc5rq3a2uzya

Discriminative Region-based Multi-Label Zero-Shot Learning [article]

Sanath Narayan, Akshita Gupta, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Mubarak Shah
2021 arXiv   pre-print
Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image.  ...  Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification.  ...  Additional Qualitative Results Multi-label zero-shot classification: Fig. 9 shows the qualitative results for multi-label (generalized) zero-shot learning.  ... 
arXiv:2108.09301v1 fatcat:gptpifksxbddraov3jfg3owmq4

Generalized Zero-shot ICD Coding [article]

Congzheng Song, Shanghang Zhang, Najmeh Sadoughi, Pengtao Xie, Eric Xing
2019 arXiv   pre-print
To the best of our knowledge, this works represents the first one that proposes an adversarial generative model for the generalized zero-shot learning on multi-label text classification.  ...  It is a multi-label text classification task with extremely long-tailed label distribution, making it difficult to perform fine-grained classification on both frequent and zero-shot codes at the same time  ...  learning on multi-label text classification.  ... 
arXiv:1909.13154v1 fatcat:epn7tamrgncxlpv2mkkesnahk4

Knowledge Extraction in Low-Resource Scenarios: Survey and Perspective [article]

Shumin Deng, Ningyu Zhang, Hui Chen, Feiyu Xiong, Jeff Z. Pan, Huajun Chen
2022 arXiv   pre-print
In addition, we describe promising applications and outline some potential directions for future research.  ...  a zero-shot learning method.  ...  ., 2018] , designed for few-shot RE, is a large-scale supervised few-shot relation classification dataset.  ... 
arXiv:2202.08063v1 fatcat:2q64tx2mzne53gt24adi6ymj7a
« Previous Showing results 1 — 15 out of 5,900 results