# Learning Semantic Ambiguities for Zero-Shot Learning

arXiv: https://arxiv.org/abs/2201.01823 · HTML: https://mlsanity.com/paper/2201.01823/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 5 Jan 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Generalized Zero-Shot Learning via Synthesized Examples](https://mlsanity.com/paper/1712.03878/) (2017)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [Ridge Regression, Hubness, and Zero-Shot Learning](https://mlsanity.com/paper/1507.00825/) (2015)
- [A Simple Exponential Family Framework for Zero-Shot Learning](https://mlsanity.com/paper/1707.08040/) (2017)
- [Generating Visual Representations for Zero-Shot Classification](https://mlsanity.com/paper/1708.06975/) (2017)
- [Multimodal Entity Linking for Tweets](https://mlsanity.com/paper/2104.03236/) (2021)
- [Semantically Aligned Bias Reducing Zero Shot Learning](https://mlsanity.com/paper/1904.07659/) (2019)
- [Learning More Universal Representations for Transfer-Learning](https://mlsanity.com/paper/1712.09708/) (2017)
- [From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process](https://mlsanity.com/paper/1809.10120/) (2018)
- [Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning](https://mlsanity.com/paper/2008.02880/) (2020)
- [Zero-shot Learning with Deep Neural Networks for Object Recognition](https://mlsanity.com/paper/2102.03137/) (2021)

## Built on by (most cited first, 2 of 2)

- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [Constraint Multi-class Positive and Unlabeled Learning for Distantly Supervised Named Entity Recognition](https://mlsanity.com/paper/2504.04963/) (2025)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the visual samples of seen classes and the corresponding semantic descriptions, in order to do the same on unseen classes at test time. State of the art approaches rely on generative models that synthesize visual features from the prototype of a class, such that a classifier can then be learned in a supervised manner. However, these approaches are usually biased towards seen classes whose visual instances are the only one that can be matched to a given class prototype. We propose a regularization method that can be applied to any conditional generative-based ZSL method, by leveraging only the semantic class prototypes. It learns to synthesize discriminative features for possible semantic description that are not available at training time, that is the unseen ones. The approach is evaluated for ZSL and GZSL on four datasets commonly used in the literature, either in inductive and transductive settings, with results on-par or above state of the art approaches.