# Self Paced Adversarial Training for Multimodal Few-shot Learning

arXiv: https://arxiv.org/abs/1811.09192 · HTML: https://mlsanity.com/paper/1811.09192/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [CLIP-guided Prototype Modulating for Few-shot Action Recognition](https://mlsanity.com/paper/2303.02982/) (2023)
- [MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition](https://mlsanity.com/paper/2305.07214/) (2023)
- [Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition](https://mlsanity.com/paper/2212.04873/) (2022)
- [Multimodality in Meta-Learning: A Comprehensive Survey](https://mlsanity.com/paper/2109.13576/) (2021)
- [HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities](https://mlsanity.com/paper/2105.07889/) (2021)
- [Explainable AI the Latest Advancements and New Trends](https://mlsanity.com/paper/2505.07005/) (2025)
- [On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization](https://mlsanity.com/paper/2405.18751/) (2024)
- [Active Multimodal Distillation for Few-shot Action Recognition](https://mlsanity.com/paper/2506.13322/) (2025)

## Abstract (arXiv)

State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes. To a certain extent this lack of data can be compensated by multimodal information. Missing information in one modality of a single data point (e.g. an image) can be made up for in another modality (e.g. a textual description). Therefore, we design a few-shot learning task that is multimodal during training (i.e. image and text) and single-modal during test time (i.e. image). In this regard, we propose a self-paced class-discriminative generative adversarial network incorporating multimodality in the context of few-shot learning. The proposed approach builds upon the idea of cross-modal data generation in order to alleviate the data sparsity problem. We improve few-shot learning accuracies on the finegrained CUB and Oxford-102 datasets.