Zero-Shot Learning via Semantic Similarity Embedding
arXiv:1509.04767
Abstract
In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based on revealed source domain side information (\eg attributes) for unseen classes. Our method is based on viewing each source or target data as a mixture of seen class proportions and we postulate that the mixture patterns have to be similar if the two instances belong to the same unseen class. This perspective leads us to learning source/target embedding functions that map an arbitrary source/target domain data into a same semantic space where similarity can be readily measured. We develop a max-margin framework to learn these similarity functions and jointly optimize parameters by means of cross validation. Our test results are compelling, leading to significant improvement in terms of accuracy on most benchmark datasets for zero-shot recognition.
arXiv commentaccepted for ICCV 2015
References in corpus (5)
Cited by in corpus (42)
- Semantic Autoencoder for Zero-Shot Learning
- Preserving Semantic Relations for Zero-Shot Learning
- Synthesized Classifiers for Zero-Shot Learning
- Zero-Shot Learning via Class-Conditioned Deep Generative Models
- Zero-Shot Learning by Generating Pseudo Feature Representations
- From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis
- Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
- Semi-supervised Zero-Shot Learning by a Clustering-based Approach
- Transductive Unbiased Embedding for Zero-Shot Learning
- Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling
- Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning
- Semantically Consistent Regularization for Zero-Shot Recognition
- Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
- Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition
- Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space
- Zero-Shot Learning with Generative Latent Prototype Model
- Learning Joint Feature Adaptation for Zero-Shot Recognition
- Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
- Modeling Long-horizon Tasks as Sequential Interaction Landscapes
- Zero-Shot Learning via Joint Latent Similarity Embedding
- Zero-Shot Sketch-Image Hashing
- Group Membership Prediction
- Zero-Shot Visual Recognition via Bidirectional Latent Embedding
- From Zero-Shot Learning to Cold-Start Recommendation
- Less is more: zero-shot learning from online textual documents with noise suppression
- Critical Assessment of Transfer Learning for Medical Image Segmentation with Fully Convolutional Neural Networks
- Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
- Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
- Zero-Shot Learning via Category-Specific Visual-Semantic Mapping
- Bi-Adversarial Auto-Encoder for Zero-Shot Learning
- Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics
- DeMIAN: Deep Modality Invariant Adversarial Network
- Global Semantic Consistency for Zero-Shot Learning
- Joint Dictionaries for Zero-Shot Learning
- AMP0: Species-Specific Prediction of Anti-microbial Peptides using Zero and Few Shot Learning
- Zero-Shot Learning via Latent Space Encoding
- Zero-Shot Learning with Multi-Battery Factor Analysis
- Composing Text and Image for Image Retrieval - An Empirical Odyssey
- Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature
- Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning
- Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection
- Hard Negative Mining for Metric Learning Based Zero-Shot Classification