Zero-Shot Learning Through Cross-Modal Transfer
arXiv:1301.3666
Abstract
This work introduces a model that can recognize objects in images even if no training data is available for the objects. The only necessary knowledge about the unseen categories comes from unsupervised large text corpora. In our zero-shot framework distributional information in language can be seen as spanning a semantic basis for understanding what objects look like. Most previous zero-shot learning models can only differentiate between unseen classes. In contrast, our model can both obtain state of the art performance on classes that have thousands of training images and obtain reasonable performance on unseen classes. This is achieved by first using outlier detection in the semantic space and then two separate recognition models. Furthermore, our model does not require any manually defined semantic features for either words or images.
References in corpus (1)
Cited by in corpus (152)
- Learning to Prompt for Vision-Language Models
- Deep Learning for Anomaly Detection: A Survey
- Recent Advances in Open Set Recognition: A Survey
- Label-Embedding for Image Classification
- Zero-Shot Learning by Convex Combination of Semantic Embeddings
- Transductive Multi-view Zero-Shot Learning
- Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
- A Review of Challenges and Opportunities in Machine Learning for Health
- Learning Factorized Multimodal Representations
- Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions
- Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
- Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review
- Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
- Supervised Multimodal Bitransformers for Classifying Images and Text
- Machine Learning for Intrusion Detection in Industrial Control Systems: Applications, Challenges, and Recommendations
- SR2CNN: Zero-Shot Learning for Signal Recognition
- Learning Deep Representations of Fine-grained Visual Descriptions
- Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
- Semantics-Guided Contrastive Network for Zero-Shot Object detection
- Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
- Zero-Shot Detection
- Hierarchically-Refined Label Attention Network for Sequence Labeling
- Zero-Shot Learning -- The Good, the Bad and the Ugly
- Representation Learning for Natural Language Processing
- tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
- Compiling Spiking Neural Networks to Neuromorphic Hardware
- Subspace Regularizers for Few-Shot Class Incremental Learning
- On the Effectiveness of Transfer Learning for Code Search
- Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
- Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning
- Cluster-based Zero-shot learning for multivariate data
- A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
- Zero-Shot Learning posed as a Missing Data Problem
- Transfer Learning for Speech and Language Processing
- Score Function Features for Discriminative Learning: Matrix and Tensor Framework
- Discrete and continuous representations and processing in deep learning: Looking forward
- What Makes Training Multi-Modal Classification Networks Hard?
- Deep Open-Set Recognition for Silicon Wafer Production Monitoring
- ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling
- Vocabulary-informed Zero-shot and Open-set Learning
- Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
- A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
- Transferable Contrastive Network for Generalized Zero-Shot Learning
- Dual Progressive Prototype Network for Generalized Zero-Shot Learning
- Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors
- Fine-Grained Zero-Shot Learning with DNA as Side Information
- Self-supervised Moving Vehicle Tracking with Stereo Sound
- Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
- Domain Adaptive Dialog Generation via Meta Learning
- Learning Translations via Matrix Completion
- Multimodal Grounding for Language Processing
- Identifying Unknown Instances for Autonomous Driving
- Learning a Deep Embedding Model for Zero-Shot Learning
- Transforming task representations to perform novel tasks
- Unsupervised Domain Adaptation of Language Models for Reading Comprehension
- Deep Tree Learning for Zero-shot Face Anti-Spoofing
- Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
- A Meta-Learning Framework for Generalized Zero-Shot Learning
- SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
- Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?
- Isometric Propagation Network for Generalized Zero-shot Learning
- Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
- Generative Replay-based Continual Zero-Shot Learning
- A Baseline Neural Machine Translation System for Indian Languages
- Generalized Continual Zero-Shot Learning
- Machine Learning with World Knowledge: The Position and Survey
- Zero-Shot Semantic Segmentation
- Attribute Propagation Network for Graph Zero-shot Learning
- Cross-Domain Adaptation for Animal Pose Estimation
- ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation
- Visual Space Optimization for Zero-shot Learning
- Region Semantically Aligned Network for Zero-Shot Learning
- Emergent Discrete Communication in Semantic Spaces
- Target inductive methods for zero-shot regression
- An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning
- CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse
- Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
- Transfer feature generating networks with semantic classes structure for zero-shot learning
- Low Emission Building Control with Zero-Shot Reinforcement Learning
- Towards Effective Deep Embedding for Zero-Shot Learning
- Adaptive Cross-Modal Few-Shot Learning
- Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning
- Knowledge-aware Zero-Shot Learning: Survey and Perspective
- Neural Word Search in Historical Manuscript Collections
- Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
- Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation
- Joint Visual-Textual Embedding for Multimodal Style Search
- Unified Generator-Classifier for Efficient Zero-Shot Learning
- A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification
- Domain-Specific Embedding Network for Zero-Shot Recognition
- Alleviating Feature Confusion for Generative Zero-shot Learning
- Visual Semantic Information Pursuit: A Survey
- ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
- SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
- Hierarchical Prototype Learning for Zero-Shot Recognition
- On Learning Semantic Representations for Million-Scale Free-Hand Sketches
- From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
- From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
- Informed Democracy: Voting-based Novelty Detection for Action Recognition
- Hyper-Process Model: A Zero-Shot Learning algorithm for Regression Problems based on Shape Analysis
- Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
- Progressive Ensemble Networks for Zero-Shot Recognition
- Natural Vocabulary Emerges from Free-Form Annotations
- Joint Concept Matching based Learning for Zero-Shot Recognition
- Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation
- Learning Invariant Representations across Domains and Tasks
- From Generalized zero-shot learning to long-tail with class descriptors
- Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval
- Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification
- Learning from Multiple Noisy Partial Labelers
- CIZSL++: Creativity Inspired Generative Zero-Shot Learning
- Improving Generalized Zero-Shot Learning by Semantic Discriminator
- BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
- Transductive Multi-class and Multi-label Zero-shot Learning
- Generalized Zero-shot Intent Detection via Commonsense Knowledge
- Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
- Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories
- Deep Zero-Shot Learning for Scene Sketch
- AlphaNet: Improving Long-Tail Classification By Combining Classifiers
- Zero-shot task adaptation by homoiconic meta-mapping
- Learning the Compositional Spaces for Generalized Zero-shot Learning
- A Zero-Shot Learning application in Deep Drawing process using Hyper-Process Model
- Convolutional Prototype Learning for Zero-Shot Recognition
- TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning
- Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning
- A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning
- Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning
- Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection
- What Remains of Visual Semantic Embeddings
- Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization
- Learning Clusterable Visual Features for Zero-Shot Recognition
- ZSTAD: Zero-Shot Temporal Activity Detection
- DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning
- Revisiting Document Representations for Large-Scale Zero-Shot Learning
- A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
- Zero-Shot Recognition via Optimal Transport
- A Review of Computer Vision Methods in Network Security
- SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning
- Unifying Few- and Zero-Shot Egocentric Action Recognition
- Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning
- Toward Zero-Shot Unsupervised Image-to-Image Translation
- Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing
- Semantic Graph for Zero-Shot Learning
- Shareable Representations for Search Query Understanding
- Zero-Shot Activity Recognition with Videos
- Autoencoder Based Sample Selection for Self-Taught Learning
- Towards Zero-shot Learning for Automatic Phonemic Transcription
- Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification
- Multiple-Kernel Dictionary Learning for Reconstruction and Clustering of Unseen Multivariate Time-series
- On zero-shot recognition of generic objects
- Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning
- Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments