Filters








1,640 Hits in 4.5 sec

Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics

Ao-Xue Li, Ke-Xin Zhang, Li-Wei Wang
2019 International Journal of Automation and Computing  
In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features.  ...  In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot  ...  Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long  ... 
doi:10.1007/s11633-019-1177-8 fatcat:o6ve4m2o6zhodje5ckhjrvfoka

Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics [article]

Aoxue Li, Zhiwu Lu, Liwei Wang, Tao Xiang, Xinqi Li, Ji-Rong Wen
2017 arXiv   pre-print
In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features.  ...  In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot  ...  A deep convolutional neural network integrating hierarchical semantic structure of classes and domain adaptation strategy is first developed for feature learning and a label propagation method based on  ... 
arXiv:1707.00785v1 fatcat:ngvnlj7z6bgf7lnfnj36mgcoii

Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning [article]

Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I-Jeng Wang
2017 arXiv   pre-print
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation.  ...  with those of posteriors based on semantic attribute estimation.  ...  Acknowledgments We thank the authors of [ ] for providing the class to attribute mapping of their data set.  ... 
arXiv:1712.03151v1 fatcat:maz4josz7baehms6ixbscowf2e

Zero-Shot Learning by Convex Combination of Semantic Embeddings [article]

Mohammad Norouzi and Tomas Mikolov and Samy Bengio and Yoram Singer and Jonathon Shlens and Andrea Frome and Greg S. Corrado and Jeffrey Dean
2014 arXiv   pre-print
Proponents of these image embedding systems have stressed their advantages over the traditional classification framing of image understanding, particularly in terms of the promise for zero-shot learning  ...  We show that this simple and direct method confers many of the advantages associated with more complex image embedding schemes, and indeed outperforms state of the art methods on the ImageNet zero-shot  ...  In both ConSE and DeViSE the convolutional neural network of Krizhevsky et al. [7] is used as the image classifier. This neural network is trained on ImageNet 2012 1K set with 1000 training labels.  ... 
arXiv:1312.5650v3 fatcat:z5ir4khulnhb3kf6gbewjpobmi

Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions

Jimmy Lei Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images.  ...  Specifically, we use text features to predict the output weights of both the convolutional and the fully connected layers in a deep convolutional neural network (CNN).  ...  Acknowledgments We gratefully acknowledge support from Samsung and NSERC.  ... 
doi:10.1109/iccv.2015.483 dblp:conf/iccv/BaSFS15 fatcat:yug3tzidzndf5ar4xewxyvawfm

Hierarchical Semantic Loss and Confidence Estimator for Visual-Semantic Embedding-Based Zero-Shot Learning

Sanghyun Seo, Juntae Kim
2019 Applied Sciences  
This paper proposes a hierarchical semantic loss and confidence estimator to more efficiently perform zero-shot learning on visual data.  ...  One approach to zero-shot learning is to embed visual data such as images and rich semantic data related to text labels of visual data into a common vector space to perform zero-shot cross-modal retrieval  ...  Figure 1 . 1 Zero-shot learning process with hierarchical semantic knowledge. Figure 1 . 1 Zero-shot learning process with hierarchical semantic knowledge.  ... 
doi:10.3390/app9153133 fatcat:qnlhu3d34reczb37zpue7ff34a

Open Vocabulary Scene Parsing

Hang Zhao, Xavier Puig, Bolei Zhou, Sanja Fidler, Antonio Torralba
2017 2017 IEEE International Conference on Computer Vision (ICCV)  
In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem.  ...  Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets.  ...  In this paper we aim at going beyond this limit and to make predictions in the wild. Zero-shot learning. Zero-shot learning addresses knowledge transfer and generalization [24, 10] .  ... 
doi:10.1109/iccv.2017.221 dblp:conf/iccv/ZhaoPZF017 fatcat:flambms24bhlrjpzms2hao4g2e

Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space [article]

Bhavan Jasani, Afshaan Mazagonwalla
2019 arXiv   pre-print
In this work, we present a body pose based zero shot action recognition network and demonstrate its performance on the NTU RGB-D dataset.  ...  Such questions are addressed by the Zero Shot Learning paradigm, where a model is trained on only a subset of classes and is evaluated on its ability to correctly classify an example from a class it has  ...  The Relation Network model, consists of two separate neural networks -attribute net and relation net.  ... 
arXiv:1911.11344v1 fatcat:5adeuam35vd5fclts2rzis3wby

Rethinking Knowledge Graph Propagation for Zero-Shot Learning [article]

Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing
2019 arXiv   pre-print
Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning.  ...  Combined with finetuning of the representations in a two-stage training approach our method outperforms state-of-the-art zero-shot learning approaches.  ...  Conclusion In contrast to previous approaches using graph convolutional neural networks for zero-shot learning, we illustrate that the task of zero-shot learning benefits from shallow networks.  ... 
arXiv:1805.11724v3 fatcat:qhg2lvdjgbbtzb4oxyxpq3spuq

A Survey on Neural-symbolic Systems [article]

Dongran Yu, Bo Yang, Dayou Liu, Hui Wang
2021 arXiv   pre-print
In this case, an ideal intelligent system--a neural-symbolic system--with high perceptual and cognitive intelligence through powerful learning and reasoning capabilities gains a growing interest in the  ...  Combining the fast computation ability of neural systems and the powerful expression ability of symbolic systems, neural-symbolic systems can perform effective learning and reasoning in multi-domain tasks  ...  The convolution neural network extracts the features of the input image and inputs it into the hierarchical prediction network.  ... 
arXiv:2111.08164v1 fatcat:bc33afiitnb73bmjtrfbdgkwpy

Table of Contents

2020 IEEE transactions on multimedia  
Image/Video/Graphics Analysis and Synthesis Hierarchical Prototype Learning for Zero-Shot Recognition . . . . . . . . . . . . . . X. Zhang, S. Gui, Z. Zhu, Y. Zhao, and J.  ...  Flow Interpretation of Deep Convolutional Neural Networks . . . . . . . . . . . . . . . . . X. Cui, D. Wang, and Z. J.  ... 
doi:10.1109/tmm.2020.3002060 fatcat:ahtcs3wqqrg7xbpyzvftvznene

Learning Deep Representations of Fine-Grained Visual Descriptions

Scott Reed, Zeynep Akata, Honglak Lee, Bernt Schiele
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Sutskever, and G. E. Hinton. ImageNet 3, 5, 7 classification with deep convolutional neural networks. In [2] Z.  ...  A very simple way to do this features can be learned efficiently with fast convolutional is to average the word embeddings of each word in the vi- networks, and temporal structure can still  ... 
doi:10.1109/cvpr.2016.13 dblp:conf/cvpr/ReedALS16 fatcat:nbnhrfhhvrbkjmncr74v3wcj5m

Open Vocabulary Scene Parsing [article]

Hang Zhao, Xavier Puig, Bolei Zhou, Sanja Fidler, Antonio Torralba
2017 arXiv   pre-print
In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem.  ...  Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets.  ...  Existing work include fully convolutional neural network (FCN) [17] , deconvolutional neural network [20] , encoder-decoder SegNet [2] , dilated neural network [3, 32] , etc.  ... 
arXiv:1703.08769v2 fatcat:tzckxmb3gfafrboieeehogm7wq

Rethinking Knowledge Graph Propagation for Zero-Shot Learning

Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning.  ...  Combined with finetuning of the representations in a two-stage training approach our method outperforms state-of-the-art zero-shot learning approaches.  ...  Conclusion In contrast to previous approaches using graph convolutional neural networks for zero-shot learning, we illustrate that the task of zero-shot learning benefits from shallow networks.  ... 
doi:10.1109/cvpr.2019.01175 dblp:conf/cvpr/KampffmeyerCLWZ19 fatcat:gw6lh7hpq5fzro4wxofy4tlgqa

Semantic Autoencoder for Zero-Shot Learning [article]

Elyor Kodirov, Tao Xiang, Shaogang Gong
2017 arXiv   pre-print
Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g.~attribute space).  ...  However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g.~attribute prediction) or classification.  ...  Sparse feature learning for [26] D. Jayaraman and K. Grauman. Zero-shot recognition with deep belief networks. In Advances in neural information pro- unreliable attributes.  ... 
arXiv:1704.08345v1 fatcat:3tlzperd2nc3vmdmmigqavdonm
« Previous Showing results 1 — 15 out of 1,640 results