# Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis

arXiv: https://arxiv.org/abs/2203.05335 · HTML: https://mlsanity.com/paper/2203.05335/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 10 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Adversarial Self-Supervised Contrastive Learning](https://mlsanity.com/paper/2006.07589/) (2020)
- [Contrastive Learning with Adversarial Examples](https://mlsanity.com/paper/2010.12050/) (2020)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [A causal view of compositional zero-shot recognition](https://mlsanity.com/paper/2006.14610/) (2020)
- [Adversarially robust transfer learning](https://mlsanity.com/paper/1905.08232/) (2019)
- [Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks](https://mlsanity.com/paper/1712.01928/) (2017)
- [Episode-based Prototype Generating Network for Zero-Shot Learning](https://mlsanity.com/paper/1909.03360/) (2019)
- [Transferable Contrastive Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/1908.05832/) (2019)
- [Generalized Zero-Shot Learning Via Over-Complete Distribution](https://mlsanity.com/paper/2004.00666/) (2020)
- [Semantics Disentangling for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.07978/) (2021)
- [A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2008.04872/) (2020)
- [From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis](https://mlsanity.com/paper/1705.01782/) (2017)
- [Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/1907.05570/) (2019)
- [Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification](https://mlsanity.com/paper/2007.05869/) (2020)
- [Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning](https://mlsanity.com/paper/1810.08332/) (2018)
- [On the Benefits of Models with Perceptually-Aligned Gradients](https://mlsanity.com/paper/2005.01499/) (2020)
- [Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature](https://mlsanity.com/paper/2008.12962/) (2020)

## Built on by (most cited first, 11 of 11)

- [Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning](https://mlsanity.com/paper/2404.14808/) (2024)
- [Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2302.00875/) (2023)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [ParsNets: A Parsimonious Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning](https://mlsanity.com/paper/2312.09709/) (2023)
- [Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition](https://mlsanity.com/paper/2402.11424/) (2024)
- [Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.01167/) (2023)
- [ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning](https://mlsanity.com/paper/2408.14868/) (2024)
- [Attribute Localization and Revision Network for Zero-Shot Learning](https://mlsanity.com/paper/2310.07548/) (2023)
- [Bridge the Gap Between Visual and Linguistic Comprehension for Generalized Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2503.23806/) (2025)
- [Few-Shot Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2507.01026/) (2025)
- [Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues](https://mlsanity.com/paper/2603.21138/) (2026)

## Abstract (arXiv)

Synthesizing pseudo samples is currently the most effective way to solve the Generalized Zero-Shot Learning (GZSL) problem. Most models achieve competitive performance but still suffer from two problems: (1) Feature confounding, the overall representations confound task-correlated and task-independent features, and existing models disentangle them in a generative way, but they are unreasonable to synthesize reliable pseudo samples with limited samples; (2) Distribution uncertainty, that massive data is needed when existing models synthesize samples from the uncertain distribution, which causes poor performance in limited samples of seen classes. In this paper, we propose a non-generative model to address these problems correspondingly in two modules: (1) Task-correlated feature disentanglement, to exclude the task-correlated features from task-independent ones by adversarial learning of domain adaption towards reasonable synthesis; (2) Controllable pseudo sample synthesis, to synthesize edge-pseudo and center-pseudo samples with certain characteristics towards more diversity generated and intuitive transfer. In addation, to describe the new scene that is the limit seen class samples in the training process, we further formulate a new ZSL task named the 'Few-shot Seen class and Zero-shot Unseen class learning' (FSZU). Extensive experiments on four benchmarks verify that the proposed method is competitive in the GZSL and the FSZU tasks.