# Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches

arXiv: https://arxiv.org/abs/2007.13314 · HTML: https://mlsanity.com/paper/2007.13314/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 27 of 27)

- [Improved Feature Distillation via Projector Ensemble](https://mlsanity.com/paper/2210.15274/) (2022)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [3D Compositional Zero-shot Learning with DeCompositional Consensus](https://mlsanity.com/paper/2111.14673/) (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)
- [Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing](https://mlsanity.com/paper/2503.10111/) (2025)
- [Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error](https://mlsanity.com/paper/2308.03003/) (2023)
- [Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.03292/) (2021)
- [A SAM-guided Two-stream Lightweight Model for Anomaly Detection](https://mlsanity.com/paper/2402.19145/) (2024)
- [Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation](https://mlsanity.com/paper/2510.09867/) (2025)
- [Region Semantically Aligned Network for Zero-Shot Learning](https://mlsanity.com/paper/2110.07130/) (2021)
- [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)
- [GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder](https://mlsanity.com/paper/2505.11882/) (2025)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [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)
- [Attribute-aware Explainable Complementary Clothing Recommendation](https://mlsanity.com/paper/2107.01655/) (2021)
- [EnHDC: Ensemble Learning for Brain-Inspired Hyperdimensional Computing](https://mlsanity.com/paper/2203.13542/) (2022)
- [Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2606.24165/) (2026)
- [Classifier Crafting: Turn Your ConvNet into a Zero-Shot Learner!](https://mlsanity.com/paper/2103.11112/) (2021)
- [Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2306.01929/) (2023)
- [SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.13100/) (2023)
- [RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2409.00511/) (2024)
- [Prototype-Guided Curriculum Learning for Zero-Shot Learning](https://mlsanity.com/paper/2508.07771/) (2025)
- [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)

Zero-shot learning (ZSL) is commonly used to address the very pervasive problem of predicting unseen classes in fine-grained image classification and other tasks. One family of solutions is to learn synthesised unseen visual samples produced by generative models from auxiliary semantic information, such as natural language descriptions. However, for most of these models, performance suffers from noise in the form of irrelevant image backgrounds. Further, most methods do not allocate a calculated weight to each semantic patch. Yet, in the real world, the discriminative power of features can be quantified and directly leveraged to improve accuracy and reduce computational complexity. To address these issues, we propose a novel framework called multi-patch generative adversarial nets (MPGAN) that synthesises local patch features and labels unseen classes with a novel weighted voting strategy. The process begins by generating discriminative visual features from noisy text descriptions for a set of predefined local patches using multiple specialist generative models. The features synthesised from each patch for unseen classes are then used to construct an ensemble of diverse supervised classifiers, each corresponding to one local patch. A voting strategy averages the probability distributions output from the classifiers and, given that some patches are more discriminative than others, a discrimination-based attention mechanism helps to weight each patch accordingly. Extensive experiments show that MPGAN has significantly greater accuracy than state-of-the-art methods.