# SAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Models

Source: [SAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Models](<https://www.sota2.com/research/paper/68fa749f1e209131cea62b29>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:13:35.838Z

Authors: Guangxi Li, Yinsheng Song, Mingkai Zheng

Published: 2024-08-29T05:33:59.000Z

## Abstract

Long-tailed distributions in image recognition pose a considerable challenge due to the severe imbalance between a few dominant classes with numerous examples and many minority classes with few samples. Recently, the use of large generative models to create synthetic data for image classification has been realized, but utilizing synthetic data to address the challenge of long-tailed recognition remains relatively unexplored. In this work, we proposed the use of synthetic data as a complement to long-tailed datasets to eliminate the impact of data imbalance. To tackle this real-synthetic mixed dataset, we designed a two-branch model that contains Synthetic-Aware and Unaware branches (SAU). The core ideas are (1) a synthetic-unaware branch for classification that mixes real and synthetic data and treats all data equally without distinguishing between them. (2) A synthetic-aware branch for improving the robustness of the feature extractor by distinguishing between real and synthetic data and learning their discrepancies. Extensive experimental results demonstrate that our method can improve the accuracy of long-tailed image recognition. Notably, our approach achieves state-of-the-art Top-1 accuracy and significantly surpasses other methods on CIFAR-10-LT and CIFAR-100-LT datasets across various imbalance factors. Our code is available at https://github.com/lgX1123/gm4lt.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.16273>)

[PDF](<https://arxiv.org/pdf/2408.16273.pdf>)
