# Adaptive Posterior Learning: few-shot learning with a surprise-based memory module

arXiv: https://arxiv.org/abs/1902.02527 · HTML: https://mlsanity.com/paper/1902.02527/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 25 of 25)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)
- [Context-enriched molecule representations improve few-shot drug discovery](https://mlsanity.com/paper/2305.09481/) (2023)
- [Prototype-Guided Memory Replay for Continual Learning](https://mlsanity.com/paper/2108.12641/) (2021)
- [Hierarchical Variational Memory for Few-shot Learning Across Domains](https://mlsanity.com/paper/2112.08181/) (2021)
- [Learning to Rectify for Robust Learning with Noisy Labels](https://mlsanity.com/paper/2111.04239/) (2021)
- [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://mlsanity.com/paper/2208.00183/) (2022)
- [Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation](https://mlsanity.com/paper/2203.11670/) (2022)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples](https://mlsanity.com/paper/2112.02763/) (2021)
- [Few-shot Continual Learning: a Brain-inspired Approach](https://mlsanity.com/paper/2104.09034/) (2021)
- [Few-shot Partial Multi-view Learning](https://mlsanity.com/paper/2105.02046/) (2021)
- [Unified Question Generation with Continual Lifelong Learning](https://mlsanity.com/paper/2201.09696/) (2022)
- [EMO: Episodic Memory Optimization for Few-Shot Meta-Learning](https://mlsanity.com/paper/2306.05189/) (2023)
- [GCCN: Global Context Convolutional Network](https://mlsanity.com/paper/2110.11664/) (2021)
- [Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling](https://mlsanity.com/paper/2205.05155/) (2022)
- [Memory in humans and deep language models: Linking hypotheses for model augmentation](https://mlsanity.com/paper/2210.01869/) (2022)
- [Fusion-based Few-Shot Morphing Attack Detection and Fingerprinting](https://mlsanity.com/paper/2210.15510/) (2022)
- [Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.11070/) (2024)
- [FLIER: Few-shot Language Image Models Embedded with Latent Representations](https://mlsanity.com/paper/2410.07648/) (2024)
- [Few-shot Learning with Global Relatedness Decoupled-Distillation](https://mlsanity.com/paper/2107.05583/) (2021)
- [A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation](https://mlsanity.com/paper/2211.01310/) (2022)
- [Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2406.00545/) (2024)
- [Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection](https://mlsanity.com/paper/2507.07994/) (2025)

## Abstract (arXiv)

The ability to generalize quickly from few observations is crucial for intelligent systems. In this paper we introduce APL, an algorithm that approximates probability distributions by remembering the most surprising observations it has encountered. These past observations are recalled from an external memory module and processed by a decoder network that can combine information from different memory slots to generalize beyond direct recall. We show this algorithm can perform as well as state of the art baselines on few-shot classification benchmarks with a smaller memory footprint. In addition, its memory compression allows it to scale to thousands of unknown labels. Finally, we introduce a meta-learning reasoning task which is more challenging than direct classification. In this setting, APL is able to generalize with fewer than one example per class via deductive reasoning.