# Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

arXiv: https://arxiv.org/abs/1906.07697 · HTML: https://mlsanity.com/paper/1906.07697/

## Key facts

- Cited by 131 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2019.

## Built on by (most cited first, 30 of 131)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Parameter Prediction for Unseen Deep Architectures](https://mlsanity.com/paper/2110.13100/) (2021)
- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights](https://mlsanity.com/paper/2209.14733/) (2022)
- [Learning a Universal Template for Few-shot Dataset Generalization](https://mlsanity.com/paper/2105.07029/) (2021)
- [Universal Representation Learning from Multiple Domains for Few-shot Classification](https://mlsanity.com/paper/2103.13841/) (2021)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [Generalizing to New Physical Systems via Context-Informed Dynamics Model](https://mlsanity.com/paper/2202.01889/) (2022)
- [Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning](https://mlsanity.com/paper/2206.06122/) (2022)
- [Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts](https://mlsanity.com/paper/2210.03885/) (2022)
- [Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition](https://mlsanity.com/paper/2101.02833/) (2021)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning](https://mlsanity.com/paper/2303.13199/) (2023)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [DualNet: Continual Learning, Fast and Slow](https://mlsanity.com/paper/2110.00175/) (2021)
- [Few-Shot Diffusion Models](https://mlsanity.com/paper/2205.15463/) (2022)
- [Adversarial Feature Augmentation for Cross-domain Few-shot Classification](https://mlsanity.com/paper/2208.11021/) (2022)
- [Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning](https://mlsanity.com/paper/2104.08808/) (2021)
- [Online Adaptation of Language Models with a Memory of Amortized Contexts](https://mlsanity.com/paper/2403.04317/) (2024)
- [ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition](https://mlsanity.com/paper/2104.03841/) (2021)
- [Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?](https://mlsanity.com/paper/2303.04143/) (2023)
- [FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification](https://mlsanity.com/paper/2206.08671/) (2022)
- [Impact of Aliasing on Generalization in Deep Convolutional Networks](https://mlsanity.com/paper/2108.03489/) (2021)
- [NP-Match: When Neural Processes meet Semi-Supervised Learning](https://mlsanity.com/paper/2207.01066/) (2022)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)

## Abstract (arXiv)

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature. The resulting approach, called CNAPs, comprises a classifier whose parameters are modulated by an adaptation network that takes the current task's dataset as input. We demonstrate that CNAPs achieves state-of-the-art results on the challenging Meta-Dataset benchmark indicating high-quality transfer-learning. We show that the approach is robust, avoiding both over-fitting in low-shot regimes and under-fitting in high-shot regimes. Timing experiments reveal that CNAPs is computationally efficient at test-time as it does not involve gradient based adaptation. Finally, we show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning.