# Learning Dynamic Alignment via Meta-filter for Few-shot Learning

arXiv: https://arxiv.org/abs/2103.13582 · HTML: https://mlsanity.com/paper/2103.13582/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 25 Mar 2021.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Augmented Neural ODEs](https://mlsanity.com/paper/1904.01681/) (2019)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Latent ODEs for Irregularly-Sampled Time Series](https://mlsanity.com/paper/1907.03907/) (2019)
- [Dissecting Neural ODEs](https://mlsanity.com/paper/2002.08071/) (2020)
- [Boosting Few-Shot Visual Learning with Self-Supervision](https://mlsanity.com/paper/1906.05186/) (2019)

## Built on by (most cited first, 30 of 41)

- [StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2302.09309/) (2023)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Rethinking Generalization in Few-Shot Classification](https://mlsanity.com/paper/2206.07267/) (2022)
- [Compound Prototype Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2207.05515/) (2022)
- [Few-Shot Classification with Contrastive Learning](https://mlsanity.com/paper/2209.08224/) (2022)
- [Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning](https://mlsanity.com/paper/2203.09064/) (2022)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Task Discrepancy Maximization for Fine-grained Few-Shot Classification](https://mlsanity.com/paper/2207.01376/) (2022)
- [Exploring Efficient Few-shot Adaptation for Vision Transformers](https://mlsanity.com/paper/2301.02419/) (2023)
- [Adaptive Poincar'e Point to Set Distance for Few-Shot Classification](https://mlsanity.com/paper/2112.01719/) (2021)
- [D4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On](https://mlsanity.com/paper/2407.15111/) (2024)
- [One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching](https://mlsanity.com/paper/2307.07286/) (2023)
- [RankDNN: Learning to Rank for Few-shot Learning](https://mlsanity.com/paper/2211.15320/) (2022)
- [MHFC: Multi-Head Feature Collaboration for Few-Shot Learning](https://mlsanity.com/paper/2109.07785/) (2021)
- [tSF: Transformer-based Semantic Filter for Few-Shot Learning](https://mlsanity.com/paper/2211.00868/) (2022)
- [MDFM: Multi-Decision Fusing Model for Few-Shot Learning](https://mlsanity.com/paper/2112.00690/) (2021)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning](https://mlsanity.com/paper/2112.03494/) (2021)
- [PatchMix Augmentation to Identify Causal Features in Few-shot Learning](https://mlsanity.com/paper/2211.16019/) (2022)
- [SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning](https://mlsanity.com/paper/2303.09281/) (2023)
- [Clustered-patch Element Connection for Few-shot Learning](https://mlsanity.com/paper/2304.10093/) (2023)
- [Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification](https://mlsanity.com/paper/2308.00093/) (2023)
- [Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment](https://mlsanity.com/paper/2507.00566/) (2025)
- [Towards Enabling Meta-Learning from Target Models](https://mlsanity.com/paper/2104.03736/) (2021)
- [Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective](https://mlsanity.com/paper/2211.00890/) (2022)
- [Few-shot Classification via Ensemble Learning with Multi-Order Statistics](https://mlsanity.com/paper/2305.00454/) (2023)
- [Disentangled Representation Learning with Transmitted Information Bottleneck](https://mlsanity.com/paper/2311.01686/) (2023)
- [Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts](https://mlsanity.com/paper/2505.15506/) (2025)
- [MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning](https://mlsanity.com/paper/2203.01482/) (2022)
- [BaseTransformers: Attention over base data-points for One Shot Learning](https://mlsanity.com/paper/2210.02476/) (2022)

## Abstract (arXiv)

Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for feature alignment in few-shot learning only consider image-level or spatial-level alignment while omitting the channel disparity. Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes. Therefore, in this paper, we propose to learn a dynamic alignment, which can effectively highlight both query regions and channels according to different local support information. Specifically, this is achieved by first dynamically sampling the neighbourhood of the feature position conditioned on the input few shot, based on which we further predict a both position-dependent and channel-dependent Dynamic Meta-filter. The filter is used to align the query feature with position-specific and channel-specific knowledge. Moreover, we adopt Neural Ordinary Differential Equation (ODE) to enable a more accurate control of the alignment. In such a sense our model is able to better capture fine-grained semantic context of the few-shot example and thus facilitates dynamical knowledge adaptation for few-shot learning. The resulting framework establishes the new state-of-the-arts on major few-shot visual recognition benchmarks, including miniImageNet and tieredImageNet.