# Task-Agnostic Meta-Learning for Few-shot Learning

arXiv: https://arxiv.org/abs/1805.07722 · HTML: https://mlsanity.com/paper/1805.07722/

## Key facts

- Cited by 151 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2018.

## Built on by (most cited first, 30 of 151)

- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners](https://mlsanity.com/paper/2303.02151/) (2023)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima](https://mlsanity.com/paper/2111.01549/) (2021)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning](https://mlsanity.com/paper/2103.01315/) (2021)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Meta-Learning with Fewer Tasks through Task Interpolation](https://mlsanity.com/paper/2106.02695/) (2021)
- [CLIP-guided Prototype Modulating for Few-shot Action Recognition](https://mlsanity.com/paper/2303.02982/) (2023)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition](https://mlsanity.com/paper/2308.03063/) (2023)
- [Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning](https://mlsanity.com/paper/2203.09064/) (2022)
- [Binocular Mutual Learning for Improving Few-shot Classification](https://mlsanity.com/paper/2108.12104/) (2021)
- [Towards Robust Physical-world Backdoor Attacks on Lane Detection](https://mlsanity.com/paper/2405.05553/) (2024)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition](https://mlsanity.com/paper/2405.02077/) (2024)
- [RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition](https://mlsanity.com/paper/2111.04566/) (2021)
- [Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2106.00184/) (2021)
- [Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes](https://mlsanity.com/paper/2208.06671/) (2022)
- [Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms](https://mlsanity.com/paper/2103.03697/) (2021)
- [MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation](https://mlsanity.com/paper/2206.09667/) (2022)
- [Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification](https://mlsanity.com/paper/2107.12262/) (2021)
- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)

## Abstract (arXiv)

Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during meta-training phase. In other words, the initial model of a meta-learner could be too biased towards existing tasks to adapt to new tasks, especially when only very few examples are available to update the model. To avoid a biased meta-learner and improve its generalizability, we propose a novel paradigm of Task-Agnostic Meta-Learning (TAML) algorithms. Specifically, we present an entropy-based approach that meta-learns an unbiased initial model with the largest uncertainty over the output labels by preventing it from over-performing in classification tasks. Alternatively, a more general inequality-minimization TAML is presented for more ubiquitous scenarios by directly minimizing the inequality of initial losses beyond the classification tasks wherever a suitable loss can be defined.Experiments on benchmarked datasets demonstrate that the proposed approaches outperform compared meta-learning algorithms in both few-shot classification and reinforcement learning tasks.