# Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning

arXiv: https://arxiv.org/abs/1904.10056 · HTML: https://mlsanity.com/paper/1904.10056/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 30 of 38)

- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [OntoZSL: Ontology-enhanced Zero-shot Learning](https://mlsanity.com/paper/2102.07339/) (2021)
- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language](https://mlsanity.com/paper/2203.03598/) (2022)
- [I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification](https://mlsanity.com/paper/2209.10304/) (2022)
- [Fine-Grained Zero-Shot Learning with DNA as Side Information](https://mlsanity.com/paper/2109.14133/) (2021)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [Temporal and cross-modal attention for audio-visual zero-shot learning](https://mlsanity.com/paper/2207.09966/) (2022)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Image-free Classifier Injection for Zero-Shot Classification](https://mlsanity.com/paper/2308.10599/) (2023)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Mitigating Generation Shifts for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.03163/) (2021)
- [Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning](https://mlsanity.com/paper/2106.00264/) (2021)
- [GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2207.01798/) (2022)
- [Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning](https://mlsanity.com/paper/2407.08130/) (2024)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)
- [A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference](https://mlsanity.com/paper/2301.09300/) (2023)
- [A Gating Model for Bias Calibration in Generalized Zero-shot Learning](https://mlsanity.com/paper/2203.04195/) (2022)
- [Semantically Grounded Visual Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2201.00577/) (2022)
- [Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning](https://mlsanity.com/paper/2407.15613/) (2024)
- [Online Lifelong Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.10741/) (2021)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2402.02094/) (2024)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [Langevin Autoencoders for Learning Deep Latent Variable Models](https://mlsanity.com/paper/2209.07036/) (2022)
- [Resolving Semantic Confusions for Improved Zero-Shot Detection](https://mlsanity.com/paper/2212.06097/) (2022)
- [Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning](https://mlsanity.com/paper/2212.13151/) (2022)
- [Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation](https://mlsanity.com/paper/2304.07918/) (2023)

## Abstract (arXiv)

We investigate learning feature-to-feature translator networks by alternating back-propagation as a general-purpose solution to zero-shot learning (ZSL) problems. It is a generative model-based ZSL framework. In contrast to models based on generative adversarial networks (GAN) or variational autoencoders (VAE) that require auxiliary networks to assist the training, our model consists of a single conditional generator that maps class-level semantic features and Gaussian white noise vector accounting for instance-level latent factors to visual features, and is trained by maximum likelihood estimation. The training process is a simple yet effective alternating back-propagation process that iterates the following two steps: (i) the inferential back-propagation to infer the latent factors of each observed example, and (ii) the learning back-propagation to update the model parameters. We show that, with slight modifications, our model is capable of learning from incomplete visual features for ZSL. We conduct extensive comparisons with existing generative ZSL methods on five benchmarks, demonstrating the superiority of our method in not only ZSL performance but also convergence speed and computational cost. Specifically, our model outperforms the existing state-of-the-art methods by a remarkable margin up to 3.1% and 4.0% in ZSL and generalized ZSL settings, respectively.