Zero-Shot Learning by Convex Combination of Semantic Embeddings.

Our method maps images into the semantic embedding space via convex combination of the class label embedding vectors, and requires no additional training. ... 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 ... The effectiveness of our method called "convex combination of semantic embeddings" (ConSE) is evaluated on ImageNet zero-shot learning task. ...

arXiv:1312.5650v3 fatcat:z5ir4khulnhb3kf6gbewjpobmi

Multiple Versions

Our method maps images into the semantic embedding space via convex combination of the class label embedding vectors, and requires no additional training. ... Proponents of these image embedding systems have stressed their advantages over the traditional n-way classification framing of image understanding, particularly in terms of the promise for zero-shot learning-the ... The effectiveness of our method called "convex combination of semantic embeddings" (ConSE) is evaluated on ImageNet zero-shot learning task. ...

fatcat:npthl7vidrg7xgf7xy7k2jhzha

We present a novel approach to tackle this ZSD problem, where a convex combination of embeddings are used in conjunction with a detection framework. ... In this study, we define a more difficult scenario, namely zero-shot object detection (ZSD) where no visual training data is available for some of the target object classes. ... [30] use convex combination of the semantic embedding vectors directly without learning any semantic space. Elhoseiny et al. ...

arXiv:1805.06157v2 fatcat:34tfhvllxbaoddgrah4hefxzsq

Multiple Versions

Building upon recent advances in few-shot learning with additional semantic information, we demonstrate that further improvements are possible by combining multiple and richer semantics (category labels ... In this paper, we focus on the role of additional semantics that can significantly facilitate few-shot visual learning. ... In [37] the semantic representation of visual categories is learned on top of the GloVe [23] word embedding, jointly with a Proto-Net [30] based few-shot classifier, and jointly with the convex combination ...

arXiv:1906.01905v2 fatcat:wqi2cd5k6recnb7kpgckloohc4

Open Access Multiple Versions

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating ... We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen ... Large-scale zero-shot learning One major limitation of most existing work on zero-shot learning is that the number of unseen classes is often small, dwarfed by the number of seen classes. ...

arXiv:1603.00550v3 fatcat:ujbmva2lgba7pi75w7e53knulq

Multiple Versions

We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen ... Given semantic descriptions of object classes, zeroshot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them ... Large-scale zero-shot learning One major limitation of most existing work on zero-shot learning is that the number of unseen classes is often small, dwarfed by the number of seen classes. ...

doi:10.1109/cvpr.2016.575 dblp:conf/cvpr/ChangpinyoCGS16 fatcat:2odd5r5ck5hhhdvguwtl7qyuu4

The empirical results show the proposed approach outperforms existing state-of-the-art zero-shot learning methods. ... Most existing zero-shot learning methods require a user to first provide a set of semantic visual attributes for each class as side information before applying a two-step prediction procedure that introduces ... Related Work In this section, we briefly review the related work on zero-shot learning and label embedding learning. Zero-Shot Learning. ...

doi:10.1109/iccv.2015.479 dblp:conf/iccv/LiGS15 fatcat:ybc53cie25d6bevv5aaskpjuce

Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. ... Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes. ... [25] forms the semantic information of unseen samples by a convex combination of seen-class semantics. ...

arXiv:1807.09123v1 fatcat:b7vpuqfua5aklfjvbutosu5kmy

Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. ... Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes. ... [23] forms the semantic information of unseen samples by a convex combination of seen-class semantics. ...

doi:10.1007/978-3-030-01249-6_8 fatcat:kwlsx742ffe7xi3okrnloqj74u

We further address the parameter tuning problem for meta-learning, especially focusing on zero-shot learning. By combining different embedded parameters, we improved the accuracy of tuned-SAE. ... In this paper, we investigate mage recognition for unseen categories of a given dataset with limited training information. We deploy a zero-shot learning (ZSL) algorithm to achieve this goal. ... ConSE takes images and maps them into the semantic embedding space using convex combination of the class label embedding vectors. ...

arXiv:2003.00837v1 fatcat:on7rogajqvd23nxw3d7sntanru

Open Access

Thus, rich semantic knowledge of the relation labels is ignored. In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification. ... To recognize unseen relations at test time, we explore the problem of zero-shot relation classification. ... This work is funded by NSFC91846204/U19B2027/61473260, national key research program 2018YFB1402800/SQ2018YFC000004, Alibaba CangJingGe (Knowledge Engine) Research Plan. ...

arXiv:2010.16068v1 fatcat:32mls4yobvdr5lzyy3wd4o2ojq

Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by ... In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. ... Zero-shot learning by convex combination of semantic embeddings. ICLR, 2014. [35] Boris N Oreshkin, Alexandre Lacoste, and Pau Rodriguez. ...

arXiv:1902.07104v3 fatcat:mmjrixwfkzg7fknqaxlgjggdki

Multiple Versions

In this paper we propose a transfer-aware embedding projection approach to tackle multi-label zero-shot learning. ... Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. ... [Norouzi et al., 2013] also took advantage of CNNs but they expressed image embeddings as convex combinations of seen class embeddings. ...

arXiv:1808.02474v1 fatcat:dov2w7ofbvdg3kdfiprkb5sm3i

We demonstrate the effectiveness of the zero-shot semantic learning algorithm on the SUC dataset collected by (Tur, 2012). ... Furthermore, we achieve state-of-the-art results by combining the semantic features with a supervised method. ... Zero-shot Discriminative Embedding (ZDE) combines the embedding method of Section 5 with the minimization of the entropy of a zero-shot classifier on that embedding. ...

arXiv:1401.0509v3 fatcat:bcri3qreyfdqtm3npsmfat77m4

Open Access Multiple Versions

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. ... We develop a max-margin framework to learn these similarity functions and jointly optimize parameters by means of cross validation. ... Department of Homeland Security, Science and Technology Directorate, Office of University Programs, under Grant Award 2013-ST-061-ED0001, by ONR Grant 50202168 and US AF contract FA8650-14-C-1728. ...

arXiv:1509.04767v2 fatcat:rfftlip5cnb7jiwnbx7cme5db4

Multiple Versions

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

Preserved Fulltext

Other Versions

Zero-Shot Learning by Convex Combination of Semantic Embeddings

Preserved Fulltext

Zero-Shot Object Detection by Hybrid Region Embedding [article]

Preserved Fulltext

Other Versions

Baby steps towards few-shot learning with multiple semantics [article]

Preserved Fulltext

Other Versions

Synthesized Classifiers for Zero-Shot Learning [article]

Preserved Fulltext

Other Versions

Synthesized Classifiers for Zero-Shot Learning

Preserved Fulltext

Semi-Supervised Zero-Shot Classification with Label Representation Learning

Preserved Fulltext

Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition [article]

Preserved Fulltext

Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition [chapter]

Preserved Fulltext

On Parameter Tuning in Meta-learning for Computer Vision [article]

Preserved Fulltext

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification [article]

Preserved Fulltext

Adaptive Cross-Modal Few-Shot Learning [article]

Preserved Fulltext

Other Versions

Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection [article]

Preserved Fulltext

Zero-Shot Learning for Semantic Utterance Classification [article]

Preserved Fulltext

Other Versions

Zero-Shot Learning via Semantic Similarity Embedding [article]

Preserved Fulltext

Other Versions