# Semantic Autoencoder for Zero-Shot Learning

arXiv: https://arxiv.org/abs/1704.08345 · HTML: https://mlsanity.com/paper/1704.08345/

## Key facts

- Cited by 133 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2017.

## Built on by (most cited first, 30 of 133)

- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Semantics Disentangling for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.07978/) (2021)
- [ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning](https://mlsanity.com/paper/2104.04697/) (2021)
- [OntoZSL: Ontology-enhanced Zero-shot Learning](https://mlsanity.com/paper/2102.07339/) (2021)
- [Knowledge-aware Zero-Shot Learning: Survey and Perspective](https://mlsanity.com/paper/2103.00070/) (2021)
- [Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2104.06601/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework](https://mlsanity.com/paper/2105.00187/) (2021)
- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training](https://mlsanity.com/paper/2104.05248/) (2021)
- [AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation](https://mlsanity.com/paper/2309.00096/) (2023)
- [Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language](https://mlsanity.com/paper/2203.03598/) (2022)
- [Dual Progressive Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2111.02073/) (2021)
- [Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style](https://mlsanity.com/paper/2303.14348/) (2023)
- [Semantic Diversity Learning for Zero-Shot Multi-label Classification](https://mlsanity.com/paper/2105.05926/) (2021)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition](https://mlsanity.com/paper/2406.13327/) (2024)
- [Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention](https://mlsanity.com/paper/2203.03483/) (2022)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Robust Region Feature Synthesizer for Zero-Shot Object Detection](https://mlsanity.com/paper/2201.00103/) (2022)
- [Hybrid Routing Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2203.15310/) (2022)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition](https://mlsanity.com/paper/2108.04603/) (2021)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research](https://mlsanity.com/paper/2211.11747/) (2022)
- [Evolving Interpretable Visual Classifiers with Large Language Models](https://mlsanity.com/paper/2404.09941/) (2024)

## Abstract (arXiv)

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.