# Associative Alignment for Few-shot Image Classification

arXiv: https://arxiv.org/abs/1912.05094 · HTML: https://mlsanity.com/paper/1912.05094/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2019.

## Built on by (most cited first, 30 of 58)

- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [Few-Shot Object Detection via Association and DIscrimination](https://mlsanity.com/paper/2111.11656/) (2021)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment](https://mlsanity.com/paper/2210.01439/) (2022)
- [Semantic Prompt for Few-Shot Image Recognition](https://mlsanity.com/paper/2303.14123/) (2023)
- [Binocular Mutual Learning for Improving Few-shot Classification](https://mlsanity.com/paper/2108.12104/) (2021)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Self-Promoted Supervision for Few-Shot Transformer](https://mlsanity.com/paper/2203.07057/) (2022)
- [Task Discrepancy Maximization for Fine-grained Few-Shot Classification](https://mlsanity.com/paper/2207.01376/) (2022)
- [Learning Expressive Prompting With Residuals for Vision Transformers](https://mlsanity.com/paper/2303.15591/) (2023)
- [Self-Supervision Can Be a Good Few-Shot Learner](https://mlsanity.com/paper/2207.09176/) (2022)
- [Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification](https://mlsanity.com/paper/2106.05517/) (2021)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [Hybrid Graph Neural Networks for Few-Shot Learning](https://mlsanity.com/paper/2112.06538/) (2021)
- [On the Importance of Distractors for Few-Shot Classification](https://mlsanity.com/paper/2109.09883/) (2021)
- [MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning](https://mlsanity.com/paper/2103.14341/) (2021)
- [Label Hallucination for Few-Shot Classification](https://mlsanity.com/paper/2112.03340/) (2021)
- [Cap2Aug: Caption guided Image to Image data Augmentation](https://mlsanity.com/paper/2212.05404/) (2022)
- [DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network](https://mlsanity.com/paper/2103.08160/) (2021)
- [CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification](https://mlsanity.com/paper/2203.13465/) (2022)
- [Multi-level Metric Learning for Few-shot Image Recognition](https://mlsanity.com/paper/2103.11383/) (2021)
- [Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images](https://mlsanity.com/paper/2105.11874/) (2021)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)
- [tSF: Transformer-based Semantic Filter for Few-Shot Learning](https://mlsanity.com/paper/2211.00868/) (2022)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)

## Abstract (arXiv)

Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes. This paper proposes the idea of associative alignment for leveraging part of the base data by aligning the novel training instances to the closely related ones in the base training set. This expands the size of the effective novel training set by adding extra "related base" instances to the few novel ones, thereby allowing a constructive fine-tuning. We propose two associative alignment strategies: 1) a metric-learning loss for minimizing the distance between related base samples and the centroid of novel instances in the feature space, and 2) a conditional adversarial alignment loss based on the Wasserstein distance. Experiments on four standard datasets and three backbones demonstrate that combining our centroid-based alignment loss results in absolute accuracy improvements of 4.4%, 1.2%, and 6.2% in 5-shot learning over the state of the art for object recognition, fine-grained classification, and cross-domain adaptation, respectively.