# Invertible Zero-Shot Recognition Flows

arXiv: https://arxiv.org/abs/2007.04873 · HTML: https://mlsanity.com/paper/2007.04873/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 30 of 48)

- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Goal-Oriented Gaze Estimation for Zero-Shot Learning](https://mlsanity.com/paper/2103.03433/) (2021)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [Improving Zero-Shot Generalization for CLIP with Synthesized Prompts](https://mlsanity.com/paper/2307.07397/) (2023)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning](https://mlsanity.com/paper/2203.01522/) (2022)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Discriminative Region-based Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2108.09301/) (2021)
- [Dual Progressive Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2111.02073/) (2021)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [Evolving Semantic Prototype Improves Generative Zero-Shot Learning](https://mlsanity.com/paper/2306.06931/) (2023)
- [Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition](https://mlsanity.com/paper/2108.04603/) (2021)
- [Mitigating Generation Shifts for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.03163/) (2021)
- [GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2207.01798/) (2022)
- [CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning](https://mlsanity.com/paper/2404.09640/) (2024)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)
- [Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation](https://mlsanity.com/paper/2112.12573/) (2021)
- [Zero-Shot Logit Adjustment](https://mlsanity.com/paper/2204.11822/) (2022)
- [Deconstructed Generation-Based Zero-Shot Model](https://mlsanity.com/paper/2204.11280/) (2022)
- [EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning](https://mlsanity.com/paper/2308.09915/) (2023)
- [SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning](https://mlsanity.com/paper/2503.10252/) (2025)
- [Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains](https://mlsanity.com/paper/2107.07497/) (2021)
- [GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder](https://mlsanity.com/paper/2505.11882/) (2025)
- [Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition](https://mlsanity.com/paper/2402.11424/) (2024)
- [On Implicit Attribute Localization for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.04704/) (2021)
- [Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2104.01832/) (2021)
- [Evolutionary Generalized Zero-Shot Learning](https://mlsanity.com/paper/2211.13174/) (2022)
- [Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.01167/) (2023)
- [PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning](https://mlsanity.com/paper/2410.11560/) (2024)

## Abstract (arXiv)

Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently. However, the underlying drawbacks of GANs and VAEs (e.g., the hardness of training with ZSL-oriented regularizers and the limited generation quality) hinder the existing generative ZSL models from fully bypassing the seen-unseen bias. To tackle the above limitations, for the first time, this work incorporates a new family of generative models (i.e., flow-based models) into ZSL. The proposed Invertible Zero-shot Flow (IZF) learns factorized data embeddings (i.e., the semantic factors and the non-semantic ones) with the forward pass of an invertible flow network, while the reverse pass generates data samples. This procedure theoretically extends conventional generative flows to a factorized conditional scheme. To explicitly solve the bias problem, our model enlarges the seen-unseen distributional discrepancy based on negative sample-based distance measurement. Notably, IZF works flexibly with either a naive Bayesian classifier or a held-out trainable one for zero-shot recognition. Experiments on widely-adopted ZSL benchmarks demonstrate the significant performance gain of IZF over existing methods, in both classic and generalized settings.