# Synthetic Sample Selection for Generalized Zero-Shot Learning

arXiv: https://arxiv.org/abs/2304.02846 · HTML: https://mlsanity.com/paper/2304.02846/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 63 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Towards Efficient Data Valuation Based on the Shapley Value](https://mlsanity.com/paper/1902.10275/) (2019)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Data Valuation using Reinforcement Learning](https://mlsanity.com/paper/1909.11671/) (2019)
- [Generalized Zero-Shot Learning via Synthesized Examples](https://mlsanity.com/paper/1712.03878/) (2017)
- [Multi-modal Cycle-consistent Generalized Zero-Shot Learning](https://mlsanity.com/paper/1808.00136/) (2018)
- [SMART Frame Selection for Action Recognition](https://mlsanity.com/paper/2012.10671/) (2020)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Episode-based Prototype Generating Network for Zero-Shot Learning](https://mlsanity.com/paper/1909.03360/) (2019)
- [Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition](https://mlsanity.com/paper/1904.08703/) (2019)
- [Learning Attributes Equals Multi-Source Domain Generalization](https://mlsanity.com/paper/1605.00743/) (2016)
- [A Generative Approach to Zero-Shot and Few-Shot Action Recognition](https://mlsanity.com/paper/1801.09086/) (2018)
- [Transductive Zero-Shot Action Recognition by Word-Vector Embedding](https://mlsanity.com/paper/1511.04458/) (2015)
- [ColorNet: Investigating the importance of color spaces for image classification](https://mlsanity.com/paper/1902.00267/) (2019)
- [Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation](https://mlsanity.com/paper/1611.08663/) (2016)

## Built on by (most cited first, 14 of 14)

- [ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning](https://mlsanity.com/paper/2406.02929/) (2024)
- [From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications](https://mlsanity.com/paper/2308.16041/) (2023)
- [Continual Learning Improves Zero-Shot Action Recognition](https://mlsanity.com/paper/2410.10497/) (2024)
- [Telling Stories for Common Sense Zero-Shot Action Recognition](https://mlsanity.com/paper/2309.17327/) (2023)
- [Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning](https://mlsanity.com/paper/2309.01390/) (2023)
- [Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring](https://mlsanity.com/paper/2407.16264/) (2024)
- [Is Temporal Prompting All We Need For Limited Labeled Action Recognition?](https://mlsanity.com/paper/2504.01890/) (2025)
- [Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification](https://mlsanity.com/paper/2504.04510/) (2025)
- [Few-Shot Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2507.01026/) (2025)
- [Fine-Grained Zero-Shot Learning with Attribute-Centric Representations](https://mlsanity.com/paper/2512.12219/) (2025)
- [ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning](https://mlsanity.com/paper/2602.12401/) (2026)
- [Novel Semantic Prompting for Zero-Shot Action Recognition](https://mlsanity.com/paper/2603.08289/) (2026)
- [CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition](https://mlsanity.com/paper/2605.01165/) (2026)
- [Can News Predict the Market? Limits of Zero-Shot Financial NLP and the Role of Explainable AI](https://mlsanity.com/paper/2606.12210/) (2026)

## Abstract (arXiv)

Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training. Despite the significant progress achieved by generative techniques in converting traditional GZSL to fully supervised learning, they tend to generate a large number of synthetic features that are often redundant, thereby increasing training time and decreasing accuracy. To address this issue, this paper proposes a novel approach for synthetic feature selection using reinforcement learning. In particular, we propose a transformer-based selector that is trained through proximal policy optimization (PPO) to select synthetic features based on the validation classification accuracy of the seen classes, which serves as a reward. The proposed method is model-agnostic and data-agnostic, making it applicable to both images and videos and versatile for diverse applications. Our experimental results demonstrate the superiority of our approach over existing feature-generating methods, yielding improved overall performance on multiple benchmarks.