Transductive Zero-Shot Recognition via Shared Model Space Learning

Zero-shot Recognition (ZSR) is to learn recognition models for novel classes without labeled data. It is a challenging task and has drawn considerable attention in recent years. The basic idea is to transfer knowledge from seen classes via the shared attributes. This paper focus on the transductive ZSR, i.e., we have unlabeled data for novel classes. Instead of learning models for seen and novel classes separately as in existing works, we put forward a novel joint learning approach which learns the shared model space (SMS) for models such that the knowledge can be effectively transferred between classes using the attributes. An effective algorithm is proposed for optimization. We conduct comprehensive experiments on three benchmark datasets for ZSR. The results demonstrates that the proposed SMS can significantly outperform the state-of-the-art related approaches which validates its efficacy for the ZSR task.

• Publication year

  2016

• Venue

  AAAI Conference on Artificial Intelligence

• Publication date

  2016-02-12

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1609/aaai.v30i1.10448
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Zero-shot object recognition by semantic manifold distance

  2015cited by this paper
• Learning Predictable and Discriminative Attributes for Visual Recognition

  2015cited by this paper
• An embarrassingly simple approach to zero-shot learning

  2015cited by this paper
• Zero-shot recognition with unreliable attributes

  2014influential reference
• Adaptation Regularization: A General Framework for Transfer Learning

  2014cited by this paper
• Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation

  2014influential reference
• VideoStory: A New Multimedia Embedding for Few-Example Recognition and Translation of Events

  2014cited by this paper
• Transfer Learning in a Transductive Setting

  2013influential reference
• Label-Embedding for Attribute-Based Classification

  2013cited by this paper
• Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions

  2013cited by this paper
• Zero-Shot Learning Through Cross-Modal Transfer

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

  2013cited by this paper
• Designing Category-Level Attributes for Discriminative Visual Recognition

  2013cited by this paper
• Zero-Shot Learning by Convex Combination of Semantic Embeddings

  2013cited by this paper
• Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost

  2013cited by this paper
• SUN attribute database: Discovering, annotating, and recognizing scene attributes

  2012cited by this paper
• Improving Word Representations via Global Context and Multiple Word Prototypes

  2012cited by this paper
• Attribute Discovery via Predictable Discriminative Binary Codes

  2012cited by this paper
• From Frequency to Meaning: Vector Space Models of Semantics

  2010cited by this paper
• Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example

  2010cited by this paper
• Zero-shot Learning with Semantic Output Codes

  2009cited by this paper
• Learning to detect unseen object classes by between-class attribute transfer

  2009cited by this paper
• Describing objects by their attributes

  2009influential reference
• Transfer Learning via Dimensionality Reduction

  2008cited by this paper
• Analysis of Representations for Domain Adaptation

  2006influential reference
• Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

  2006cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• A comparison of methods for multiclass support vector machines

  2002cited by this paper
• Information Retrieval using a Singular Value Decomposition Model of Latent Semantic Structure

  1988cited by this paper
• This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Learning Multi-modal Latent At

  year unknowninfluential reference
• Attribute-Based Classification for Zero-Shot Visual Object Categorization

  year unknowninfluential reference

• Generative Model-Based Mixed-Semantic Enhancement for Transductive Zero-Shot Learning

  2026cites this paper
• Bias-Alleviated Zero-Shot Sports Action Recognition Enabled by Multi-Scale Semantic Alignment

  2025cites this paper
• Neighbourhood clustering for enhancing domain-adaptive zero-shot learning and beyond

  2025cites this paper
• Transductive Learning With Prior Knowledge for Generalized Zero-Shot Action Recognition

  2024cites this paper
• Consistency-guided pseudo labeling for transductive zero-shot learning

  2024cites this paper
• On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

  2024cites this paper
• IndusSynthe: Synthetic data using human-machine intelligence hybrid for enhanced industrial surface defect detection through self-updating with multi-view filtering

  2024cites this paper
• A zero-shot quantitative evaluation model for subsurface defects size based on ultrasonic nondestructive testing

  2024cites this paper
• Human–machine knowledge hybrid augmentation method for surface defect detection based few-data learning

  2023cites this paper
• Regularized label relaxation-based stacked autoencoder for zero-shot learning

  2023cites this paper
• Towards Zero-Shot Learning: A Brief Review and an Attention-Based Embedding Network

  2023cites this paper
• See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

  2023cites this paper
• Semantic Consistent Embedding for Domain Adaptive Zero-Shot Learning

  2023cites this paper
• Information bottleneck and selective noise supervision for zero-shot learning

  2022cites this paper
• A study on zero-shot learning from semantic viewpoint

  2022cites this paper
• Hyperspectral Imaging Zero-Shot Learning for Remote Marine Litter Detection and Classification

  2022cites this paper
• Exploring Attribute Space with Word Embedding for Zero-shot Learning

  2022cites this paper
• GAN-MVAE: A discriminative latent feature generation framework for generalized zero-shot learning

  2022cites this paper
• Context-sensitive zero-shot semantic segmentation model based on meta-learning

  2021cites this paper
• Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding

  2021cites this paper
• Handling new target classes in semantic segmentation with domain adaptation

  2021cites this paper
• Zero-shot learning compound fault diagnosis of bearings

  2021cites this paper
• An Iterative Co-Training Transductive Framework for Zero Shot Learning

  2021influential citation
• Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization

  2021cites this paper
• Zero-Shot Learning on 3D Point Cloud Objects and Beyond

  2021cites this paper
• VMAN: A Virtual Mainstay Alignment Network for Transductive Zero-Shot Learning

  2021cites this paper
• Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning

  2021cites this paper
• Generalized Zero-Shot Learning With Multiple Graph Adaptive Generative Networks

  2021cites this paper
• Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization

  2021cites this paper
• Deep transductive network for generalized zero shot learning

  2020cites this paper
• Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition

  2020cites this paper
• Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

  2020cites this paper
• Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning

  2020influential citation
• Bidirectional generative transductive zero-shot learning

  2020cites this paper
• Domain-aware Stacked AutoEncoders for zero-shot learning

  2020cites this paper
• Few-Shot Zero-Shot Learning: Knowledge Transfer with Less Supervision

  2020cites this paper
• Zero-shot learning by mutual information estimation and maximization

  2020cites this paper
• A Variational Autoencoder with Deep Embedding Model for Generalized Zero-Shot Learning

  2020cites this paper
• Learning cross-domain semantic-visual relationships for transductive zero-shot learning

  2020influential citation
• Similarity preserving feature generating networks for zero-shot learning

  2020cites this paper
• Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning

  2020cites this paper
• Research progress of zero-shot learning

  2020cites this paper
• Zero-VAE-GAN: Generating Unseen Features for Generalized and Transductive Zero-Shot Learning

  2020cites this paper
• Disentangled features with direct sum decomposition for zero shot learning

  2020cites this paper
• A General Transductive Regularizer for Zero-Shot Learning

  2019cites this paper
• Zero-Shot Learning via Category-Specific Visual-Semantic Mapping and Label Refinement

  2019influential citation
• Triple Verification Network for Generalized Zero-Shot Learning

  2019cites this paper
• Dual-verification network for zero-shot learning

  2019cites this paper
• Transductive Zero-Shot Learning with Visual Structure Constraint

  2019cites this paper
• Generic compact representation through visual-semantic ambiguity removal

  2019cites this paper
• Zero-shot Hashing with orthogonal projection for image retrieval

  2019cites this paper
• A Survey of Zero-Shot Learning

  2019cites this paper
• Adversarial unseen visual feature synthesis for Zero-shot Learning

  2019cites this paper
• Zero-shot multi-label learning via label factorisation

  2019cites this paper
• Dual-View Ranking with Hardness Assessment for Zero-Shot Learning

  2019cites this paper
• Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

  2019influential citation
• Feature Selection via Transferring Knowledge Across Different Classes

  2019cites this paper
• Visual Space Optimization for Zero-shot Learning

  2019cites this paper
• Attentive Region Embedding Network for Zero-Shot Learning

  2019cites this paper
• Landmark Selection for Zero-shot Learning

  2019cites this paper
• Cross-domain mapping learning for transductive zero-shot learning

  2019cites this paper
• Image Feature Extractor Image Feature Class Feature Output Softmax Weight Factor Branch Feature Branch Softmax

  2019cites this paper
• Transductive Learning for Zero-Shot Object Detection

  2019influential citation
• Convolutional Prototype Learning for Zero-Shot Recognition

  2019cites this paper
• Hierarchical Prototype Learning for Zero-Shot Recognition

  2019cites this paper
• Attribute Attention for Semantic Disambiguation in Zero-Shot Learning

  2019cites this paper
• Beyond Attributes: High-Order Attribute Features for Zero-Shot Learning

  2019cites this paper
• A decadal survey of zero-shot image classification

  2019cites this paper
• Sensor-based human activity recognition via zero-shot learning

  2019cites this paper
• A Probabilistic Zero-Shot Learning Method via Latent Nonnegative Prototype Synthesis of Unseen Classes

  2019cites this paper
• Safe semi supervised multi-target regression (MTR-SAFER) for new targets learning

  2018cites this paper
• Transductive Unbiased Embedding for Zero-Shot Learning

  2018cites this paper
• Multi-Modal Coreference Resolution with the Correlation between Space Structures

  2018cites this paper
• Implicit Non-linear Similarity Scoring for Recognizing Unseen Classes

  2018cites this paper
• Extreme Reverse Projection Learning for Zero-Shot Recognition

  2018cites this paper
• Self-Training Ensemble Networks for Zero-Shot Image Recognition

  2018cites this paper
• Zero-Shot Learning: An Energy Based Approach

  2018cites this paper
• Ja n 20 18 A Simple Exponential Family Framework for Zero-Shot Learning

  2018cites this paper
• Zero-Shot Learning with Sparse Attribute Propagation

  2018cites this paper
• Zero-Shot Learning with Superclasses

  2018cites this paper
• Zero-shot leaning and hashing with binary visual similes

  2018cites this paper
• Learning Semantic Double-Autoencoder with Attribute Constraint for Zero-Shot Recognition

  2018cites this paper
• Progressive Ensemble Networks for Zero-Shot Recognition

  2018cites this paper
• Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning

  2018influential citation
• Domain-Invariant Projection Learning for Zero-Shot Recognition

  2018cites this paper
• Zero and Few Shot Learning With Semantic Feature Synthesis and Competitive Learning

  2018cites this paper
• Cross-class transfer learning for visual data

  2017cites this paper
• Semantic Space Yorkshire Beagle Cairn Collie Kelpie Pug Visual Space Beagle Yorkshire Pug Collie Kelpie Cairn : Seen Class : Unseen Class A S A F : Seen Class Image : Unseen Class Image

  2017influential citation
• Zero-Shot Recognition via Direct Classifier Learning with Transferred Samples and Pseudo Labels

  2017influential citation
• Learning Autoencoder of Attribute Constraint for Zero-Shot Classification

  2017influential citation
• Zero-Shot Learning via Category-Specific Visual-Semantic Mapping

  2017influential citation
• Synthesizing Samples for Zero-shot Learning

  2017cites this paper
• Zero-shot classification by transferring knowledge and preserving data structure

  2017cites this paper
• Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining

  2017cites this paper
• Elephant Panda Lion Dolphin Dog Monkey ... ... Classes Elephant Dolphin Lion Classifier Training Data Synthesizing Prediction

  2017cites this paper
• A Simple Exponential Family Framework for Zero-Shot Learning

  2017cites this paper
• Boosted Zero-Shot Learning with Semantic Correlation Regularization

  2017cites this paper
• Transductive Zero-Shot Learning With Adaptive Structural Embedding

  2017influential citation
• Zero-Shot Learning With Transferred Samples

  2017cites this paper
• Transductive Zero-Shot Learning With a Self-Training Dictionary Approach

  2017cites this paper