Semantic Autoencoder for Zero-Shot Learning
arXiv:1704.08345
Abstract
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. When applied to test data, which in the context of ZSL contains different (unseen) classes without training data, a ZSL model typically suffers from the project domain shift problem. In this work, we present a novel solution to ZSL based on learning a Semantic AutoEncoder (SAE). Taking the encoder-decoder paradigm, an encoder aims to project a visual feature vector into the semantic space as in the existing ZSL models. However, the decoder exerts an additional constraint, that is, the projection/code must be able to reconstruct the original visual feature. We show that with this additional reconstruction constraint, the learned projection function from the seen classes is able to generalise better to the new unseen classes. Importantly, the encoder and decoder are linear and symmetric which enable us to develop an extremely efficient learning algorithm. Extensive experiments on six benchmark datasets demonstrate that the proposed SAE outperforms significantly the existing ZSL models with the additional benefit of lower computational cost. Furthermore, when the SAE is applied to supervised clustering problem, it also beats the state-of-the-art.
accepted to CVPR2017
References in corpus (5)
Cited by in corpus (36)
- Leveraging the Invariant Side of Generative Zero-Shot Learning
- Preserving Semantic Relations for Zero-Shot Learning
- Zero-Shot Learning via Class-Conditioned Deep Generative Models
- Polarity Loss for Zero-shot Object Detection
- Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning
- Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
- Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition
- Information flows of diverse autoencoders
- Zero-Shot Sketch-Image Hashing
- Generalized Zero-Shot Recognition based on Visually Semantic Embedding
- Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations
- Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval
- Visual Space Optimization for Zero-shot Learning
- A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning
- Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
- Domain segmentation and adjustment for generalized zero-shot learning
- Generative Dual Adversarial Network for Generalized Zero-shot Learning
- Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
- Bi-Adversarial Auto-Encoder for Zero-Shot Learning
- Global Semantic Consistency for Zero-Shot Learning
- Alleviating Feature Confusion for Generative Zero-shot Learning
- Joint Dictionaries for Zero-Shot Learning
- Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval
- Spatial Priming for Detecting Human-Object Interactions
- AMP0: Species-Specific Prediction of Anti-microbial Peptides using Zero and Few Shot Learning
- Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation
- OntoZSL: Ontology-enhanced Zero-shot Learning
- Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
- CIZSL++: Creativity Inspired Generative Zero-Shot Learning
- Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning
- Learning the Compositional Spaces for Generalized Zero-shot Learning
- Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
- Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
- Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature
- Learning Clusterable Visual Features for Zero-Shot Recognition
- Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning