---
title: "自动背景交换：抵御虚假背景的鲁棒性方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2606.32018v1"
permalink: "https://feed.astralor.com/items/itm_f9337e0c56616f26d8d4123a"
published: "2026-06-30T17:50:24.000Z"
score: 55
channel: "ai"
tags: ["AutoBackSwap","图像分类","数据增强","鲁棒性"]
---

# 自动背景交换：抵御虚假背景的鲁棒性方法

## 速览

本文提出AutoBackSwap方法，通过辅助网络分离前景与背景，利用图像补全生成完整背景，并交换不同前景与背景来增强训练数据。仅需少量样本的补丁标注即可训练辅助网络，自动扩充整个训练集。在多种图像分类任务中，即使训练数据中没有打破虚假相关的样本，AutoBackSwap也能有效减少分类器对背景的依赖，显著优于以往方法。

## 关键点

- 利用辅助网络分离前景与背景，结合图像补全生成真实背景。
- 仅需数百张样本的补丁标注即可训练辅助网络，实现全数据集自动增强。
- 即使训练数据中没有打破虚假背景相关的样本，仍能有效提升鲁棒性。
- 在多个图像分类任务上一致超越现有方法。

## 全文

Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.e., features that are predictive of the target label in the training data but are not causally linked and thus fail to generalize. For the vision domain, many such spurious correlations manifest themselves within the background of the image, where only the foreground is predictive of the class label. In this paper, we introduce Automated Background Swapping (AutoBackSwap) to reduce the reliance of classifiers on such spurious backgrounds. AutoBackSwap uses a secondary network to disentangle the foreground and background, followed by infilling to synthesize complete backgrounds, and finally combines different foregrounds and inpainted backgrounds to augment the training data. We find that patch-wise labeling of just a few hundred samples suffices to train the secondary network and automatically augment the full training dataset on challenging image classification tasks. In contrast to many previous methods, AutoBackSwap proves very effective even if there is not a single sample in the training data breaking the spurious correlation. Across a range of image classification tasks with spurious backgrounds, AutoBackSwap consistently outperforms prior methods.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_f9337e0c56616f26d8d4123a