# Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

arXiv: https://arxiv.org/abs/2107.09249 · HTML: https://mlsanity.com/paper/2107.09249/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 68 references that are in the map.
- First posted on arXiv 20 Jul 2021.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [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)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [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)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [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)
- [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)
- [Training independent subnetworks for robust prediction](https://mlsanity.com/paper/2010.06610/) (2020)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses](https://mlsanity.com/paper/2003.08983/) (2020)
- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis](https://mlsanity.com/paper/2007.07222/) (2020)
- [Learning Loss for Test-Time Augmentation](https://mlsanity.com/paper/2010.11422/) (2020)

## Built on by (most cited first, 30 of 95)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Empowering Graph Representation Learning with Test-Time Graph Transformation](https://mlsanity.com/paper/2210.03561/) (2022)
- [Expanding Small-Scale Datasets with Guided Imagination](https://mlsanity.com/paper/2211.13976/) (2022)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization](https://mlsanity.com/paper/2309.14949/) (2023)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning](https://mlsanity.com/paper/2202.05613/) (2022)
- [A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization](https://mlsanity.com/paper/2310.04752/) (2023)
- [Implicit Concept Removal of Diffusion Models](https://mlsanity.com/paper/2310.05873/) (2023)
- [Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts](https://mlsanity.com/paper/2308.08810/) (2023)
- [Balanced Product of Calibrated Experts for Long-Tailed Recognition](https://mlsanity.com/paper/2206.05260/) (2022)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [One-Shot Diffusion Mimicker for Handwritten Text Generation](https://mlsanity.com/paper/2409.04004/) (2024)
- [MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition](https://mlsanity.com/paper/2308.09922/) (2023)
- [Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction](https://mlsanity.com/paper/2310.19011/) (2023)
- [Joint Vision-Language Social Bias Removal for CLIP](https://mlsanity.com/paper/2411.12785/) (2024)
- [MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection](https://mlsanity.com/paper/2309.14976/) (2023)
- [DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations](https://mlsanity.com/paper/2405.07780/) (2024)
- [Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data](https://mlsanity.com/paper/2502.10381/) (2025)
- [Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification](https://mlsanity.com/paper/2505.01660/) (2025)
- [Decoupled Training for Long-Tailed Classification With Stochastic Representations](https://mlsanity.com/paper/2304.09426/) (2023)
- [Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning](https://mlsanity.com/paper/2312.15702/) (2023)
- [Towards Distribution-Agnostic Generalized Category Discovery](https://mlsanity.com/paper/2310.01376/) (2023)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [A Survey of Deep Long-Tail Classification Advancements](https://mlsanity.com/paper/2404.15593/) (2024)
- [Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning](https://mlsanity.com/paper/2308.01698/) (2023)
- [CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2403.10391/) (2024)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning](https://mlsanity.com/paper/2406.11890/) (2024)

## Abstract (arXiv)

Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class distributions often violate this assumption (e.g., being either long-tailed or even inversely long-tailed), which may lead existing methods to fail in real applications. In this paper, we study a more practical yet challenging task, called test-agnostic long-tailed recognition, where the training class distribution is long-tailed while the test class distribution is agnostic and not necessarily uniform. In addition to the issue of class imbalance, this task poses another challenge: the class distribution shift between the training and test data is unknown. To tackle this task, we propose a novel approach, called Self-supervised Aggregation of Diverse Experts, which consists of two strategies: (i) a new skill-diverse expert learning strategy that trains multiple experts from a single and stationary long-tailed dataset to separately handle different class distributions; (ii) a novel test-time expert aggregation strategy that leverages self-supervision to aggregate the learned multiple experts for handling unknown test class distributions. We theoretically show that our self-supervised strategy has a provable ability to simulate test-agnostic class distributions. Promising empirical results demonstrate the effectiveness of our method on both vanilla and test-agnostic long-tailed recognition. Code is available at urlhttps://github.com/Vanint/SADE-AgnosticLT.