# Long-tail Recognition via Compositional Knowledge Transfer

arXiv: https://arxiv.org/abs/2112.06741 · HTML: https://mlsanity.com/paper/2112.06741/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [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)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [How Well Do Self-Supervised Models Transfer?](https://mlsanity.com/paper/2011.13377/) (2020)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [ResLT: Residual Learning for Long-tailed Recognition](https://mlsanity.com/paper/2101.10633/) (2021)
- [ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot](https://mlsanity.com/paper/2108.02385/) (2021)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [RSG: A Simple but Effective Module for Learning Imbalanced Datasets](https://mlsanity.com/paper/2106.09859/) (2021)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)

## Built on by (most cited first, 16 of 16)

- [Unbiased Scene Graph Generation in Videos](https://mlsanity.com/paper/2304.00733/) (2023)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [Learning Imbalanced Data with Vision Transformers](https://mlsanity.com/paper/2212.02015/) (2022)
- [Towards Open-Set Text Recognition via Label-to-Prototype Learning](https://mlsanity.com/paper/2203.05179/) (2022)
- [Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds](https://mlsanity.com/paper/2303.12307/) (2023)
- [SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail](https://mlsanity.com/paper/2304.00101/) (2023)
- [Learning from Neighbors: Category Extrapolation for Long-Tail Learning](https://mlsanity.com/paper/2410.15980/) (2024)
- [RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classification](https://mlsanity.com/paper/2308.02335/) (2023)
- [Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks](https://mlsanity.com/paper/2407.08567/) (2024)
- [LTRL: Boosting Long-tail Recognition via Reflective Learning](https://mlsanity.com/paper/2407.12568/) (2024)
- [Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning](https://mlsanity.com/paper/2310.10090/) (2023)
- [Fractal Calibration for long-tailed object detection](https://mlsanity.com/paper/2410.11774/) (2024)
- [Set Learning for Accurate and Calibrated Models](https://mlsanity.com/paper/2307.02245/) (2023)
- [Towards Effective Collaborative Learning in Long-Tailed Recognition](https://mlsanity.com/paper/2305.03378/) (2023)
- [Compositional Servoing by Recombining Demonstrations](https://mlsanity.com/paper/2310.04271/) (2023)
- [Comparing Importance Sampling Based Methods for Mitigating the Effect of Class Imbalance](https://mlsanity.com/paper/2402.18742/) (2024)

## Abstract (arXiv)

In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes in order to obtain stronger tail class representations. We leverage the fact that class prototypes and learned cosine classifiers provide two different, complementary representations of class cluster centres in feature space, and use an attention mechanism to select and recompose learned classifier features from common classes to obtain higher quality rare class representations. Our knowledge transfer process is training free, reducing overfitting risks, and can afford continual extension of classifiers to new classes. Experiments show that our approach can achieve significant performance boosts on rare classes while maintaining robust common class performance, outperforming directly comparable state-of-the-art models.