面向不平衡自动驾驶任务的大模型在线无样本持续学习
Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task
AI总结：
针对自动驾驶中的在线持续学习面临的灾难性遗忘和数据不平衡问题，提出解析无样本在线持续学习算法AEF-OCL，利用岭回归分类器和伪特征生成器，在SODA10M数据集上超越多种方法。
摘要：
在自动驾驶中，即使经过精心训练的模型在遇到不熟悉场景时也可能遭遇失败。其中一种场景可被形式化为在线持续学习（OCL）问题。即，数据以在线方式到达，模型根据这些流式数据进行更新。OCL面临的两大挑战是灾难性遗忘和数据不平衡。为解决这些挑战，本文提出了一种解析无样本在线持续学习算法（AEF-OCL）。AEF-OCL利用解析持续学习原理，并采用岭回归作为由大型骨干网络提取特征的分类器。它通过递归计算解析解来解决OCL问题，确保持续学习与其联合学习对应物之间的均衡，且无需保存任何已用样本（即无样本）。此外，我们引入了一个伪特征生成器（PFG）模块，该模块递归估计每个类别的真实特征的均值和方差。它从与真实特征相同的正态分布中过采样偏移伪特征，从而解决数据不平衡问题。实验结果表明，尽管是一种无样本策略，我们的方法在自动驾驶SODA10M数据集上优于多种方法。源代码可在https://github.com/ZHUANGHP/Analytic-continual-learning获取。
英文摘要：
In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online fashion, and models are updated according to these streaming data. Two major OCL challenges are catastrophic forgetting and data imbalance. To address these challenges, in this paper, we propose an Analytic Exemplar-Free Online Continual Learning algorithm (AEF-OCL). The AEF-OCL leverages analytic continual learning principles and employs ridge regression as a classifier for features extracted by a large backbone network. It solves the OCL problem by recursively calculating the analytical solution, ensuring an equalization between the continual learning and its joint-learning counterpart, and works without the need to save any used samples (i.e., exemplar-free). Additionally, we introduce a Pseudo-Features Generator (PFG) module that recursively estimates the mean and the variance of real features for each class. It over-samples offset pseudo-features from the same normal distribution as the real features, thereby addressing the data imbalance issue. Experimental results demonstrate that despite being an exemplar-free strategy, our method outperforms various methods on the autonomous driving SODA10M dataset. Source code is available at https://github.com/ZHUANGHP/Analytic-continual-learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
