# TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

arXiv: https://arxiv.org/abs/1904.05967 · HTML: https://mlsanity.com/paper/1904.05967/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2019.

## Built on by (most cited first, 30 of 32)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Learning to Predict Visual Attributes in the Wild](https://mlsanity.com/paper/2106.09707/) (2021)
- [Universal-Prototype Enhancing for Few-Shot Object Detection](https://mlsanity.com/paper/2103.01077/) (2021)
- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection](https://mlsanity.com/paper/2203.13903/) (2022)
- [Few-shot Learning with Noisy Labels](https://mlsanity.com/paper/2204.05494/) (2022)
- [The Functional Correspondence Problem](https://mlsanity.com/paper/2109.01097/) (2021)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Zero-Shot Compositional Concept Learning](https://mlsanity.com/paper/2107.05176/) (2021)
- [Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2308.04016/) (2023)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks](https://mlsanity.com/paper/2107.02378/) (2021)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)
- [Learning Single/Multi-Attribute of Object with Symmetry and Group](https://mlsanity.com/paper/2110.04603/) (2021)
- [Pretext Tasks selection for multitask self-supervised speech representation learning](https://mlsanity.com/paper/2107.00594/) (2021)
- [CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.16681/) (2023)
- [Supervised Momentum Contrastive Learning for Few-Shot Classification](https://mlsanity.com/paper/2101.11058/) (2021)
- [MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning](https://mlsanity.com/paper/2206.06460/) (2022)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings](https://mlsanity.com/paper/2312.15086/) (2023)
- [Episode Adaptive Embedding Networks for Few-shot Learning](https://mlsanity.com/paper/2106.09398/) (2021)
- [Translational Concept Embedding for Generalized Compositional Zero-shot Learning](https://mlsanity.com/paper/2112.10871/) (2021)
- [External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery](https://mlsanity.com/paper/2107.10504/) (2021)
- [Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification](https://mlsanity.com/paper/2206.08150/) (2022)

## Abstract (arXiv)

Learning good feature embeddings for images often requires substantial training data. As a consequence, in settings where training data is limited (e.g., few-shot and zero-shot learning), we are typically forced to use a generic feature embedding across various tasks. Ideally, we want to construct feature embeddings that are tuned for the given task. In this work, we propose Task-Aware Feature Embedding Networks (TAFE-Nets) to learn how to adapt the image representation to a new task in a meta learning fashion. Our network is composed of a meta learner and a prediction network. Based on a task input, the meta learner generates parameters for the feature layers in the prediction network so that the feature embedding can be accurately adjusted for that task. We show that TAFE-Net is highly effective in generalizing to new tasks or concepts and evaluate the TAFE-Net on a range of benchmarks in zero-shot and few-shot learning. Our model matches or exceeds the state-of-the-art on all tasks. In particular, our approach improves the prediction accuracy of unseen attribute-object pairs by 4 to 15 points on the challenging visual attribute-object composition task.