# Mitigating Generation Shifts for Generalized Zero-Shot Learning

arXiv: https://arxiv.org/abs/2107.03163 · HTML: https://mlsanity.com/paper/2107.03163/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 69 references that are in the map.
- First posted on arXiv 7 Jul 2021.

## Builds on (most cited first, 30 of 38)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (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)
- [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)
- [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts](https://mlsanity.com/paper/1712.01381/) (2017)
- [Multi-modal Cycle-consistent Generalized Zero-Shot Learning](https://mlsanity.com/paper/1808.00136/) (2018)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2003.13261/) (2020)
- [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)
- [Generative Dual Adversarial Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/1811.04857/) (2018)
- [Semantics Disentangling for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.07978/) (2021)
- [Invertible Zero-Shot Recognition Flows](https://mlsanity.com/paper/2007.04873/) (2020)
- [Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.10056/) (2019)
- [A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2008.04872/) (2020)
- [From Zero-Shot Learning to Cold-Start Recommendation](https://mlsanity.com/paper/1906.08511/) (2019)
- [Adversarial Bipartite Graph Learning for Video Domain Adaptation](https://mlsanity.com/paper/2007.15829/) (2020)
- [Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches](https://mlsanity.com/paper/2007.13314/) (2020)
- [CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language](https://mlsanity.com/paper/1909.09822/) (2019)

## Built on by (most cited first, 13 of 13)

- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2207.01798/) (2022)
- [Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error](https://mlsanity.com/paper/2308.03003/) (2023)
- [GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2309.00923/) (2023)
- [SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning](https://mlsanity.com/paper/2503.10252/) (2025)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [Distributed Zero-Shot Learning for Visual Recognition](https://mlsanity.com/paper/2511.08170/) (2025)
- [Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction](https://mlsanity.com/paper/2606.24156/) (2026)
- [Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2606.24165/) (2026)
- [Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2203.02648/) (2022)
- [Fine-Grained Zero-Shot Learning with Attribute-Centric Representations](https://mlsanity.com/paper/2512.12219/) (2025)
- [StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components](https://mlsanity.com/paper/2602.00703/) (2026)

## Abstract (arXiv)

Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. It is natural to derive generative models and hallucinate training samples for unseen classes based on the knowledge learned from the seen samples. However, most of these models suffer from the `generation shifts', where the synthesized samples may drift from the real distribution of unseen data. In this paper, we conduct an in-depth analysis on this issue and propose a novel Generation Shifts Mitigating Flow (GSMFlow) framework, which is comprised of multiple conditional affine coupling layers for learning unseen data synthesis efficiently and effectively. In particular, we identify three potential problems that trigger the generation shifts, i.e., semantic inconsistency, variance decay, and structural permutation and address them respectively. First, to reinforce the correlations between the generated samples and the respective attributes, we explicitly embed the semantic information into the transformations in each of the coupling layers. Second, to recover the intrinsic variance of the synthesized unseen features, we introduce a visual perturbation strategy to diversify the intra-class variance of generated data and hereby help adjust the decision boundary of the classifier. Third, to avoid structural permutation in the semantic space, we propose a relative positioning strategy to manipulate the attribute embeddings, guiding which to fully preserve the inter-class geometric structure. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings. Our code is available at: https://github.com/uqzhichen/GSMFlow