EMNLP Findings2021
Data-Efficient Language Shaped Few-shot Image Classification
Zhenwen Liang, Xiangliang Zhang
Abstract
Many existing works have demonstrated that language is a helpful guider for image understanding by neural networks. We focus on a language-shaped learning problem in a fewshot setting, i.e., using language to improve few-shot image classification when language descriptions are only available during training. We propose a data-efficient method that can make the best usage of the few-shot images and the language available only in training. Experimental results on dataset ShapeWorld and Birds show that our method outperforms other state-of-the-art baselines in language-shaped few-shot learning area, especially when training data is more severely limited. Therefore, we call our approach data-efficient languageshaped learning (DF-LSL).
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Related papers
- Efficient Training of Language Models using Few-Shot LearningSashank J. Reddi, Sobhan Miryoosefi, Stefani Karp, Shankar Krishnan et al.ICML 2023 · 22 citations
- Semantic Prompt for Few-Shot Image RecognitionCVPR 2023
- Language Semantic Graph Guided Data-Efficient LearningWenxuan Ma, Shuang Li, Lincan Cai, Jingxuan KangNeurIPS 2023 · 6 citations
- SSAT-Adapter: Enhancing Vision-Language Model Few-shot Learning with Auxiliary TasksBowen Chen, Yun Sing Koh, Gillian DobbieACM MM 2024 · 1 citation
- Verbalized Representation Learning for Interpretable Few-Shot GeneralizationCheng-Fu Yang, Da Yin, Wenbo Hu, Heng Ji et al.ICCV 2025 · 1 citation
